diff --git a/CHANGELOG.md b/CHANGELOG.md
index 481e1fc98fca90092797330ed71c738ecff28fe2..2e73bfe8e860d3a11beb10082bbf99027700f00e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,25 @@ Unreleased
- Added detection confidence to langauge detection endpoint
- Set mel generation to adjust n_dims automatically to match the loaded model
+### Added
+
+ - Refactor classes, Add comments, implement abstract methods, and add factory method for engine selection
+
+### Changed
+
+- Upgraded
+ - [SYSTRAN/faster-whisper](https://github.com/SYSTRAN/faster-whisper) to [v1.1.0](https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.1.0)
+ - uvicorn to v0.34.0
+ - tqdm to v4.67.1
+ - python-multipart to v0.0.20
+ - fastapi to v0.115.6
+ - pytest to v8.3.4
+ - ruff to v0.8.3
+ - black to v24.10.0
+ - mkdocs to v1.6.1
+ - mkdocs-material to v9.5.49
+ - pymdown-extensions to v10.12
+
[1.6.0] (2024-10-06)
--------------------
diff --git a/app/asr_models/asr_model.py b/app/asr_models/asr_model.py
new file mode 100644
index 0000000000000000000000000000000000000000..fc2205083ed48e5e88267aeb3afa1de2d2e61051
--- /dev/null
+++ b/app/asr_models/asr_model.py
@@ -0,0 +1,71 @@
+import gc
+import time
+from abc import ABC, abstractmethod
+from threading import Lock
+from typing import Union
+
+import torch
+
+from app.config import CONFIG
+
+
+class ASRModel(ABC):
+ """
+ Abstract base class for ASR (Automatic Speech Recognition) models.
+ """
+ model = None
+ model_lock = Lock()
+ last_activity_time = time.time()
+
+ def __init__(self):
+ pass
+
+ @abstractmethod
+ def load_model(self):
+ """
+ Loads the model from the specified path.
+ """
+ pass
+
+ @abstractmethod
+ def transcribe(self,
+ audio,
+ task: Union[str, None],
+ language: Union[str, None],
+ initial_prompt: Union[str, None],
+ vad_filter: Union[bool, None],
+ word_timestamps: Union[bool, None]
+ ):
+ """
+ Perform transcription on the given audio file.
+ """
+ pass
+
+ @abstractmethod
+ def language_detection(self, audio):
+ """
+ Perform language detection on the given audio file.
+ """
+ pass
+
+ def monitor_idleness(self):
+ """
+ Monitors the idleness of the ASR model and releases the model if it has been idle for too long.
+ """
+ if CONFIG.MODEL_IDLE_TIMEOUT <= 0: return
+ while True:
+ time.sleep(15)
+ if time.time() - self.last_activity_time > CONFIG.MODEL_IDLE_TIMEOUT:
+ with self.model_lock:
+ self.release_model()
+ break
+
+ def release_model(self):
+ """
+ Unloads the model from memory and clears any cached GPU memory.
+ """
+ del self.model
+ torch.cuda.empty_cache()
+ gc.collect()
+ self.model = None
+ print("Model unloaded due to timeout")
diff --git a/app/asr_models/faster_whisper_engine.py b/app/asr_models/faster_whisper_engine.py
new file mode 100644
index 0000000000000000000000000000000000000000..a0b8620281373058002b0d893d5a00ddbe4b2ef4
--- /dev/null
+++ b/app/asr_models/faster_whisper_engine.py
@@ -0,0 +1,96 @@
+import time
+from io import StringIO
+from threading import Thread
+from typing import BinaryIO, Union
+
+import whisper
+from faster_whisper import WhisperModel
+
+from app.asr_models.asr_model import ASRModel
+from app.config import CONFIG
+from app.utils import ResultWriter, WriteJSON, WriteSRT, WriteTSV, WriteTXT, WriteVTT
+
+
+class FasterWhisperASR(ASRModel):
+
+ def load_model(self):
+
+ self.model = WhisperModel(
+ model_size_or_path=CONFIG.MODEL_NAME,
+ device=CONFIG.DEVICE,
+ compute_type=CONFIG.MODEL_QUANTIZATION,
+ download_root=CONFIG.MODEL_PATH
+ )
+
+ Thread(target=self.monitor_idleness, daemon=True).start()
+
+ def transcribe(
+ self,
+ audio,
+ task: Union[str, None],
+ language: Union[str, None],
+ initial_prompt: Union[str, None],
+ vad_filter: Union[bool, None],
+ word_timestamps: Union[bool, None],
+ output,
+ ):
+ self.last_activity_time = time.time()
+
+ with self.model_lock:
+ if self.model is None: self.load_model()
+
+ options_dict = {"task": task}
+ if language:
+ options_dict["language"] = language
+ if initial_prompt:
+ options_dict["initial_prompt"] = initial_prompt
+ if vad_filter:
+ options_dict["vad_filter"] = True
+ if word_timestamps:
+ options_dict["word_timestamps"] = True
+ with self.model_lock:
+ segments = []
+ text = ""
+ segment_generator, info = self.model.transcribe(audio, beam_size=5, **options_dict)
+ for segment in segment_generator:
+ segments.append(segment)
+ text = text + segment.text
+ result = {"language": options_dict.get("language", info.language), "segments": segments, "text": text}
+
+ output_file = StringIO()
+ self.write_result(result, output_file, output)
+ output_file.seek(0)
+
+ return output_file
+
+ def language_detection(self, audio):
+
+ self.last_activity_time = time.time()
+
+ with self.model_lock:
+ if self.model is None: self.load_model()
+
+ # load audio and pad/trim it to fit 30 seconds
+ audio = whisper.pad_or_trim(audio)
+
+ # detect the spoken language
+ with self.model_lock:
+ segments, info = self.model.transcribe(audio, beam_size=5)
+ detected_lang_code = info.language
+ detected_language_confidence = info.language_probability
+
+ return detected_lang_code, detected_language_confidence
+
+ def write_result(self, result: dict, file: BinaryIO, output: Union[str, None]):
+ if output == "srt":
+ WriteSRT(ResultWriter).write_result(result, file=file)
+ elif output == "vtt":
+ WriteVTT(ResultWriter).write_result(result, file=file)
+ elif output == "tsv":
+ WriteTSV(ResultWriter).write_result(result, file=file)
+ elif output == "json":
+ WriteJSON(ResultWriter).write_result(result, file=file)
+ elif output == "txt":
+ WriteTXT(ResultWriter).write_result(result, file=file)
+ else:
+ return "Please select an output method!"
diff --git a/app/asr_models/openai_whisper_engine.py b/app/asr_models/openai_whisper_engine.py
new file mode 100644
index 0000000000000000000000000000000000000000..c6c37dc9346ec4380d12507259f87b41fdea695e
--- /dev/null
+++ b/app/asr_models/openai_whisper_engine.py
@@ -0,0 +1,95 @@
+import time
+from io import StringIO
+from threading import Thread
+from typing import BinaryIO, Union
+
+import torch
+import whisper
+from whisper.utils import ResultWriter, WriteJSON, WriteSRT, WriteTSV, WriteTXT, WriteVTT
+
+from app.asr_models.asr_model import ASRModel
+from app.config import CONFIG
+
+
+class OpenAIWhisperASR(ASRModel):
+
+ def load_model(self):
+
+ if torch.cuda.is_available():
+ self.model = whisper.load_model(
+ name=CONFIG.MODEL_NAME,
+ download_root=CONFIG.MODEL_PATH
+ ).cuda()
+ else:
+ self.model = whisper.load_model(
+ name=CONFIG.MODEL_NAME,
+ download_root=CONFIG.MODEL_PATH
+ )
+
+ Thread(target=self.monitor_idleness, daemon=True).start()
+
+ def transcribe(
+ self,
+ audio,
+ task: Union[str, None],
+ language: Union[str, None],
+ initial_prompt: Union[str, None],
+ vad_filter: Union[bool, None],
+ word_timestamps: Union[bool, None],
+ output,
+ ):
+ self.last_activity_time = time.time()
+
+ with self.model_lock:
+ if self.model is None: self.load_model()
+
+ options_dict = {"task": task}
+ if language:
+ options_dict["language"] = language
+ if initial_prompt:
+ options_dict["initial_prompt"] = initial_prompt
+ if word_timestamps:
+ options_dict["word_timestamps"] = word_timestamps
+ with self.model_lock:
+ result = self.model.transcribe(audio, **options_dict)
+
+ output_file = StringIO()
+ self.write_result(result, output_file, output)
+ output_file.seek(0)
+
+ return output_file
+
+ def language_detection(self, audio):
+
+ self.last_activity_time = time.time()
+
+ with self.model_lock:
+ if self.model is None: self.load_model()
+
+ # load audio and pad/trim it to fit 30 seconds
+ audio = whisper.pad_or_trim(audio)
+
+ # make log-Mel spectrogram and move to the same device as the model
+ mel = whisper.log_mel_spectrogram(audio, self.model.dims.n_mels).to(self.model.device)
+
+ # detect the spoken language
+ with self.model_lock:
+ _, probs = self.model.detect_language(mel)
+ detected_lang_code = max(probs, key=probs.get)
+
+ return detected_lang_code, probs[max(probs)]
+
+ def write_result(self, result: dict, file: BinaryIO, output: Union[str, None]):
+ options = {"max_line_width": 1000, "max_line_count": 10, "highlight_words": False}
+ if output == "srt":
+ WriteSRT(ResultWriter).write_result(result, file=file, options=options)
+ elif output == "vtt":
+ WriteVTT(ResultWriter).write_result(result, file=file, options=options)
+ elif output == "tsv":
+ WriteTSV(ResultWriter).write_result(result, file=file, options=options)
+ elif output == "json":
+ WriteJSON(ResultWriter).write_result(result, file=file, options=options)
+ elif output == "txt":
+ WriteTXT(ResultWriter).write_result(result, file=file, options=options)
+ else:
+ return "Please select an output method!"
diff --git a/app/config.py b/app/config.py
new file mode 100644
index 0000000000000000000000000000000000000000..64202697feb58f622ddf3f8a0270cc38ba851262
--- /dev/null
+++ b/app/config.py
@@ -0,0 +1,37 @@
+import os
+
+import torch
+
+
+class CONFIG:
+ """
+ Configuration class for ASR models.
+ Reads environment variables for runtime configuration, with sensible defaults.
+ """
+ # Determine the ASR engine ('faster_whisper' or 'openai_whisper')
+ ASR_ENGINE = os.getenv("ASR_ENGINE", "openai_whisper")
+
+ # Determine the computation device (GPU or CPU)
+ DEVICE = os.getenv("ASR_DEVICE", "cuda" if torch.cuda.is_available() else "cpu")
+
+ # Model name to use (e.g., "base", "small", etc.)
+ MODEL_NAME = os.getenv("ASR_MODEL", "base")
+
+ # Path to the model directory
+ MODEL_PATH = os.getenv("ASR_MODEL_PATH", os.path.join(os.path.expanduser("~"), ".cache", "whisper"))
+
+ # Model quantization level. Defines the precision for model weights:
+ # 'float32' - 32-bit floating-point precision (higher precision, slower inference)
+ # 'float16' - 16-bit floating-point precision (lower precision, faster inference)
+ # 'int8' - 8-bit integer precision (lowest precision, fastest inference)
+ # Defaults to 'float32' for GPU availability, 'int8' for CPU.
+ MODEL_QUANTIZATION = os.getenv("ASR_QUANTIZATION", "float32" if torch.cuda.is_available() else "int8")
+ if MODEL_QUANTIZATION not in {"float32", "float16", "int8"}:
+ raise ValueError("Invalid MODEL_QUANTIZATION. Choose 'float32', 'float16', or 'int8'.")
+
+ # Idle timeout in seconds. If set to a non-zero value, the model will be unloaded
+ # after being idle for this many seconds. A value of 0 means the model will never be unloaded.
+ MODEL_IDLE_TIMEOUT = int(os.getenv("MODEL_IDLE_TIMEOUT", 0))
+
+ # Default sample rate for audio input. 16 kHz is commonly used in speech-to-text tasks.
+ SAMPLE_RATE = int(os.getenv("SAMPLE_RATE", 16000))
diff --git a/app/factory/asr_model_factory.py b/app/factory/asr_model_factory.py
new file mode 100644
index 0000000000000000000000000000000000000000..0f97fb53ae0a5ca20caec09dc40c388efcdb863a
--- /dev/null
+++ b/app/factory/asr_model_factory.py
@@ -0,0 +1,15 @@
+from app.asr_models.asr_model import ASRModel
+from app.asr_models.faster_whisper_engine import FasterWhisperASR
+from app.asr_models.openai_whisper_engine import OpenAIWhisperASR
+from app.config import CONFIG
+
+
+class ASRModelFactory:
+ @staticmethod
+ def create_asr_model() -> ASRModel:
+ if CONFIG.ASR_ENGINE == "openai_whisper":
+ return OpenAIWhisperASR()
+ elif CONFIG.ASR_ENGINE == "faster_whisper":
+ return FasterWhisperASR()
+ else:
+ raise ValueError(f"Unsupported ASR engine: {CONFIG.ASR_ENGINE}")
diff --git a/app/faster_whisper/core.py b/app/faster_whisper/core.py
deleted file mode 100644
index 5871d3bb87188112c4c7dec2a9dded3001921af9..0000000000000000000000000000000000000000
--- a/app/faster_whisper/core.py
+++ /dev/null
@@ -1,132 +0,0 @@
-import os
-from io import StringIO
-from threading import Lock, Thread
-from typing import BinaryIO, Union
-import time
-import gc
-
-import torch
-import whisper
-from faster_whisper import WhisperModel
-
-from .utils import ResultWriter, WriteJSON, WriteSRT, WriteTSV, WriteTXT, WriteVTT
-
-model_name = os.getenv("ASR_MODEL", "base")
-model_path = os.getenv("ASR_MODEL_PATH", os.path.join(os.path.expanduser("~"), ".cache", "whisper"))
-model = None
-model_lock = Lock()
-
-# More about available quantization levels is here:
-# https://opennmt.net/CTranslate2/quantization.html
-
-last_activity_time = time.time()
-idle_timeout = int(os.getenv("IDLE_TIMEOUT", 0)) # default to being disabled
-
-def monitor_idleness():
- global model
- if(idle_timeout <= 0): return
- while True:
- time.sleep(15)
- if time.time() - last_activity_time > idle_timeout:
- with model_lock:
- release_model()
- break
-
-def load_model():
- global model, device, model_quantization
-
- if torch.cuda.is_available():
- device = "cuda"
- model_quantization = os.getenv("ASR_QUANTIZATION", "float32")
- else:
- device = "cpu"
- model_quantization = os.getenv("ASR_QUANTIZATION", "int8")
-
- model = WhisperModel(
- model_size_or_path=model_name, device=device, compute_type=model_quantization, download_root=model_path
- )
-
- Thread(target=monitor_idleness, daemon=True).start()
-
-load_model()
-
-def release_model():
- global model
- del model
- torch.cuda.empty_cache()
- gc.collect()
- model = None
- print("Model unloaded due to timeout")
-
-def transcribe(
- audio,
- task: Union[str, None],
- language: Union[str, None],
- initial_prompt: Union[str, None],
- vad_filter: Union[bool, None],
- word_timestamps: Union[bool, None],
- output,
-):
- global last_activity_time
- last_activity_time = time.time()
-
- with model_lock:
- if(model is None): load_model()
-
- options_dict = {"task": task}
- if language:
- options_dict["language"] = language
- if initial_prompt:
- options_dict["initial_prompt"] = initial_prompt
- if vad_filter:
- options_dict["vad_filter"] = True
- if word_timestamps:
- options_dict["word_timestamps"] = True
- with model_lock:
- segments = []
- text = ""
- segment_generator, info = model.transcribe(audio, beam_size=5, **options_dict)
- for segment in segment_generator:
- segments.append(segment)
- text = text + segment.text
- result = {"language": options_dict.get("language", info.language), "segments": segments, "text": text}
-
- output_file = StringIO()
- write_result(result, output_file, output)
- output_file.seek(0)
-
- return output_file
-
-
-def language_detection(audio):
- global last_activity_time
- last_activity_time = time.time()
-
- with model_lock:
- if(model is None): load_model()
-
- # load audio and pad/trim it to fit 30 seconds
- audio = whisper.pad_or_trim(audio)
-
- # detect the spoken language
- with model_lock:
- segments, info = model.transcribe(audio, beam_size=5)
- detected_lang_code = info.language
- detected_language_confidence = info.language_probability
-
- return detected_lang_code, detected_language_confidence
-
-
-def write_result(result: dict, file: BinaryIO, output: Union[str, None]):
- if output == "srt":
- WriteSRT(ResultWriter).write_result(result, file=file)
- elif output == "vtt":
- WriteVTT(ResultWriter).write_result(result, file=file)
- elif output == "tsv":
- WriteTSV(ResultWriter).write_result(result, file=file)
- elif output == "json":
- WriteJSON(ResultWriter).write_result(result, file=file)
- elif output == "txt":
- WriteTXT(ResultWriter).write_result(result, file=file)
- else:
- return "Please select an output method!"
diff --git a/app/openai_whisper/core.py b/app/openai_whisper/core.py
deleted file mode 100644
index 1380e8423fbd06b73f7534c4ed8b9a7c3ce91af6..0000000000000000000000000000000000000000
--- a/app/openai_whisper/core.py
+++ /dev/null
@@ -1,116 +0,0 @@
-import os
-from io import StringIO
-from threading import Lock, Thread
-from typing import BinaryIO, Union
-import time
-import gc
-
-import torch
-import whisper
-from whisper.utils import ResultWriter, WriteJSON, WriteSRT, WriteTSV, WriteTXT, WriteVTT
-
-model_name = os.getenv("ASR_MODEL", "base")
-model_path = os.getenv("ASR_MODEL_PATH", os.path.join(os.path.expanduser("~"), ".cache", "whisper"))
-model = None
-model_lock = Lock()
-
-last_activity_time = time.time()
-idle_timeout = int(os.getenv("IDLE_TIMEOUT", 0)) # default to being disabled
-
-def monitor_idleness():
- global model
- if(idle_timeout <= 0): return
- while True:
- time.sleep(15) # check every minute
- if time.time() - last_activity_time > idle_timeout:
- with model_lock:
- release_model()
- break
-
-def load_model():
- global model
-
- if torch.cuda.is_available():
- model = whisper.load_model(model_name, download_root=model_path).cuda()
- else:
- model = whisper.load_model(model_name, download_root=model_path)
-
- Thread(target=monitor_idleness, daemon=True).start()
-
-load_model()
-
-def release_model():
- global model
- del model
- torch.cuda.empty_cache()
- gc.collect()
- model = None
- print("Model unloaded due to timeout")
-
-def transcribe(
- audio,
- task: Union[str, None],
- language: Union[str, None],
- initial_prompt: Union[str, None],
- vad_filter: Union[bool, None],
- word_timestamps: Union[bool, None],
- output,
-):
- global last_activity_time
- last_activity_time = time.time()
-
- with model_lock:
- if(model is None): load_model()
-
- options_dict = {"task": task}
- if language:
- options_dict["language"] = language
- if initial_prompt:
- options_dict["initial_prompt"] = initial_prompt
- if word_timestamps:
- options_dict["word_timestamps"] = word_timestamps
- with model_lock:
- result = model.transcribe(audio, **options_dict)
-
- output_file = StringIO()
- write_result(result, output_file, output)
- output_file.seek(0)
-
- return output_file
-
-
-def language_detection(audio):
- global last_activity_time
- last_activity_time = time.time()
-
- with model_lock:
- if(model is None): load_model()
-
- # load audio and pad/trim it to fit 30 seconds
- audio = whisper.pad_or_trim(audio)
-
- # make log-Mel spectrogram and move to the same device as the model
- mel = whisper.log_mel_spectrogram(audio, model.dims.n_mels).to(model.device)
-
- # detect the spoken language
- with model_lock:
- _, probs = model.detect_language(mel)
- detected_lang_code = max(probs, key=probs.get)
-
- return detected_lang_code, probs[max(probs)]
-
-
-def write_result(result: dict, file: BinaryIO, output: Union[str, None]):
- options = {"max_line_width": 1000, "max_line_count": 10, "highlight_words": False}
- if output == "srt":
- WriteSRT(ResultWriter).write_result(result, file=file, options=options)
- elif output == "vtt":
- WriteVTT(ResultWriter).write_result(result, file=file, options=options)
- elif output == "tsv":
- WriteTSV(ResultWriter).write_result(result, file=file, options=options)
- elif output == "json":
- WriteJSON(ResultWriter).write_result(result, file=file, options=options)
- elif output == "txt":
- WriteTXT(ResultWriter).write_result(result, file=file, options=options)
- else:
- return "Please select an output method!"
diff --git a/app/faster_whisper/utils.py b/app/utils.py
similarity index 67%
rename from app/faster_whisper/utils.py
rename to app/utils.py
index 034c63937a304372999f0b9b60793e04208e5d5e..0b51281a0793aef2063ad475fd8a42b05ab94481 100644
--- a/app/faster_whisper/utils.py
+++ b/app/utils.py
@@ -1,9 +1,13 @@
import json
import os
-from typing import TextIO
+from typing import TextIO, BinaryIO
+import ffmpeg
+import numpy as np
from faster_whisper.utils import format_timestamp
+from app.config import CONFIG
+
class ResultWriter:
extension: str
@@ -85,3 +89,36 @@ class WriteJSON(ResultWriter):
def write_result(self, result: dict, file: TextIO):
json.dump(result, file)
+
+
+def load_audio(file: BinaryIO, encode=True, sr: int = CONFIG.SAMPLE_RATE):
+ """
+ Open an audio file object and read as mono waveform, resampling as necessary.
+ Modified from https://github.com/openai/whisper/blob/main/whisper/audio.py to accept a file object
+ Parameters
+ ----------
+ file: BinaryIO
+ The audio file like object
+ encode: Boolean
+ If true, encode audio stream to WAV before sending to whisper
+ sr: int
+ The sample rate to resample the audio if necessary
+ Returns
+ -------
+ A NumPy array containing the audio waveform, in float32 dtype.
+ """
+ if encode:
+ try:
+ # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
+ # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
+ out, _ = (
+ ffmpeg.input("pipe:", threads=0)
+ .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sr)
+ .run(cmd="ffmpeg", capture_stdout=True, capture_stderr=True, input=file.read())
+ )
+ except ffmpeg.Error as e:
+ raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
+ else:
+ out = file.read()
+
+ return np.frombuffer(out, np.int16).flatten().astype(np.float32) / 32768.0
diff --git a/app/webservice.py b/app/webservice.py
index fce652cd1a98fefc006459b068ecc7bd8bc70581..7158645a467702a07baf8b997ce825712863ccf1 100644
--- a/app/webservice.py
+++ b/app/webservice.py
@@ -1,12 +1,10 @@
import importlib.metadata
import os
from os import path
-from typing import Annotated, BinaryIO, Optional, Union
+from typing import Annotated, Optional, Union
from urllib.parse import quote
import click
-import ffmpeg
-import numpy as np
import uvicorn
from fastapi import FastAPI, File, Query, UploadFile, applications
from fastapi.openapi.docs import get_swagger_ui_html
@@ -14,13 +12,13 @@ from fastapi.responses import RedirectResponse, StreamingResponse
from fastapi.staticfiles import StaticFiles
from whisper import tokenizer
-ASR_ENGINE = os.getenv("ASR_ENGINE", "openai_whisper")
-if ASR_ENGINE == "faster_whisper":
- from app.faster_whisper.core import language_detection, transcribe
-else:
- from app.openai_whisper.core import language_detection, transcribe
+from app.config import CONFIG
+from app.factory.asr_model_factory import ASRModelFactory
+from app.utils import load_audio
+
+asr_model = ASRModelFactory.create_asr_model()
+asr_model.load_model()
-SAMPLE_RATE = 16000
LANGUAGE_CODES = sorted(tokenizer.LANGUAGES.keys())
projectMetadata = importlib.metadata.metadata("whisper-asr-webservice")
@@ -37,6 +35,7 @@ assets_path = os.getcwd() + "/swagger-ui-assets"
if path.exists(assets_path + "/swagger-ui.css") and path.exists(assets_path + "/swagger-ui-bundle.js"):
app.mount("/assets", StaticFiles(directory=assets_path), name="static")
+
def swagger_monkey_patch(*args, **kwargs):
return get_swagger_ui_html(
*args,
@@ -46,6 +45,7 @@ if path.exists(assets_path + "/swagger-ui.css") and path.exists(assets_path + "/
swagger_js_url="/assets/swagger-ui-bundle.js",
)
+
applications.get_swagger_ui_html = swagger_monkey_patch
@@ -56,29 +56,29 @@ async def index():
@app.post("/asr", tags=["Endpoints"])
async def asr(
- audio_file: UploadFile = File(...), # noqa: B008
- encode: bool = Query(default=True, description="Encode audio first through ffmpeg"),
- task: Union[str, None] = Query(default="transcribe", enum=["transcribe", "translate"]),
- language: Union[str, None] = Query(default=None, enum=LANGUAGE_CODES),
- initial_prompt: Union[str, None] = Query(default=None),
- vad_filter: Annotated[
- bool | None,
- Query(
- description="Enable the voice activity detection (VAD) to filter out parts of the audio without speech",
- include_in_schema=(True if ASR_ENGINE == "faster_whisper" else False),
- ),
- ] = False,
- word_timestamps: bool = Query(default=False, description="Word level timestamps"),
- output: Union[str, None] = Query(default="txt", enum=["txt", "vtt", "srt", "tsv", "json"]),
+ audio_file: UploadFile = File(...), # noqa: B008
+ encode: bool = Query(default=True, description="Encode audio first through ffmpeg"),
+ task: Union[str, None] = Query(default="transcribe", enum=["transcribe", "translate"]),
+ language: Union[str, None] = Query(default=None, enum=LANGUAGE_CODES),
+ initial_prompt: Union[str, None] = Query(default=None),
+ vad_filter: Annotated[
+ bool | None,
+ Query(
+ description="Enable the voice activity detection (VAD) to filter out parts of the audio without speech",
+ include_in_schema=(True if CONFIG.ASR_ENGINE == "faster_whisper" else False),
+ ),
+ ] = False,
+ word_timestamps: bool = Query(default=False, description="Word level timestamps"),
+ output: Union[str, None] = Query(default="txt", enum=["txt", "vtt", "srt", "tsv", "json"]),
):
- result = transcribe(
+ result = asr_model.transcribe(
load_audio(audio_file.file, encode), task, language, initial_prompt, vad_filter, word_timestamps, output
)
return StreamingResponse(
result,
media_type="text/plain",
headers={
- "Asr-Engine": ASR_ENGINE,
+ "Asr-Engine": CONFIG.ASR_ENGINE,
"Content-Disposition": f'attachment; filename="{quote(audio_file.filename)}.{output}"',
},
)
@@ -86,44 +86,13 @@ async def asr(
@app.post("/detect-language", tags=["Endpoints"])
async def detect_language(
- audio_file: UploadFile = File(...), # noqa: B008
- encode: bool = Query(default=True, description="Encode audio first through FFmpeg"),
+ audio_file: UploadFile = File(...), # noqa: B008
+ encode: bool = Query(default=True, description="Encode audio first through FFmpeg"),
):
- detected_lang_code, confidence = language_detection(load_audio(audio_file.file, encode))
- return {"detected_language": tokenizer.LANGUAGES[detected_lang_code], "language_code": detected_lang_code, "confidence": confidence}
-
-
-def load_audio(file: BinaryIO, encode=True, sr: int = SAMPLE_RATE):
- """
- Open an audio file object and read as mono waveform, resampling as necessary.
- Modified from https://github.com/openai/whisper/blob/main/whisper/audio.py to accept a file object
- Parameters
- ----------
- file: BinaryIO
- The audio file like object
- encode: Boolean
- If true, encode audio stream to WAV before sending to whisper
- sr: int
- The sample rate to resample the audio if necessary
- Returns
- -------
- A NumPy array containing the audio waveform, in float32 dtype.
- """
- if encode:
- try:
- # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
- # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
- out, _ = (
- ffmpeg.input("pipe:", threads=0)
- .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sr)
- .run(cmd="ffmpeg", capture_stdout=True, capture_stderr=True, input=file.read())
- )
- except ffmpeg.Error as e:
- raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
- else:
- out = file.read()
-
- return np.frombuffer(out, np.int16).flatten().astype(np.float32) / 32768.0
+ detected_lang_code, confidence = asr_model.language_detection(load_audio(audio_file.file, encode))
+ return {"detected_language": tokenizer.LANGUAGES[detected_lang_code], "language_code": detected_lang_code,
+ "confidence": confidence}
+
@click.command()
@click.option(
@@ -142,10 +111,11 @@ def load_audio(file: BinaryIO, encode=True, sr: int = SAMPLE_RATE):
)
@click.version_option(version=projectMetadata["Version"])
def start(
- host: str,
- port: Optional[int] = None
+ host: str,
+ port: Optional[int] = None
):
uvicorn.run(app, host=host, port=port)
+
if __name__ == "__main__":
start()
diff --git a/docs/environmental-variables.md b/docs/environmental-variables.md
index 91bc35b95a8e7c651a2bb9d6aa337f3de579d708..d786927b8f861b806517443e7110eae85f7e7e33 100644
--- a/docs/environmental-variables.md
+++ b/docs/environmental-variables.md
@@ -1,13 +1,13 @@
### Configuring the `Engine`
=== ":octicons-file-code-16: `openai_whisper`"
- ```sh
- export ASR_ENGINE=openai_whisper
- ```
+```sh
+export ASR_ENGINE=openai_whisper
+```
=== ":octicons-file-code-16: `faster_whisper`"
- ```sh
- export ASR_ENGINE=faster_whisper
- ```
+```sh
+export ASR_ENGINE=faster_whisper
+```
### Configuring the `Model`
@@ -15,9 +15,10 @@
export ASR_MODEL=base
```
-Available ASR_MODELs are `tiny`, `base`, `small`, `medium`, `large`, `large-v1`, `large-v2`, `large-v3`, `turbo`(only OpenAI Whisper) and `large-v3-turbo`(only OpenAI Whisper).
+Available ASR_MODELs are `tiny`, `base`, `small`, `medium`, `large`, `large-v1`, `large-v2`, `large-v3`, `turbo` and `large-v3-turbo`.
-For English-only applications, the `.en` models tend to perform better, especially for the `tiny.en` and `base.en` models. We observed that the difference becomes less significant for the `small.en` and `medium.en` models.
+For English-only applications, the `.en` models tend to perform better, especially for the `tiny.en` and `base.en`
+models. We observed that the difference becomes less significant for the `small.en` and `medium.en` models.
### Configuring the `Model Path`
@@ -28,7 +29,18 @@ export ASR_MODEL_PATH=/data/whisper
### Configuring the `Model Unloading Timeout`
```sh
-export IDLE_TIMEOUT=300
+export MODEL_IDLE_TIMEOUT=300
```
-Defaults to 0. After no activity for this period (in seconds), unload the model until it is requested again. Setting `0` disables the timeout, keeping the model loaded indefinitely.
+Defaults to `0`. After no activity for this period (in seconds), unload the model until it is requested again. Setting
+`0` disables the timeout, keeping the model loaded indefinitely.
+
+### Configuring the `SAMPLE_RATE`
+
+```sh
+export SAMPLE_RATE=16000
+```
+
+Defaults to `16000`. Default sample rate for audio input. `16 kHz` is commonly used in `speech-to-text` tasks.
+
+
diff --git a/poetry.lock b/poetry.lock
index 914b15207643bd18cea413c5bedf0a8434d7ddb4..2b4f5de337cf20c909f94cdf546b56d8cf497ecc 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -21,34 +21,6 @@ doc = ["Sphinx", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-
test = ["anyio[trio]", "coverage[toml] (>=4.5)", "hypothesis (>=4.0)", "mock (>=4)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
trio = ["trio (<0.22)"]
-[[package]]
-name = "atomicwrites"
-version = "1.4.1"
-description = "Atomic file writes."
-optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
-files = [
- {file = "atomicwrites-1.4.1.tar.gz", hash = "sha256:81b2c9071a49367a7f770170e5eec8cb66567cfbbc8c73d20ce5ca4a8d71cf11"},
-]
-
-[[package]]
-name = "attrs"
-version = "23.1.0"
-description = "Classes Without Boilerplate"
-optional = false
-python-versions = ">=3.7"
-files = [
- {file = "attrs-23.1.0-py3-none-any.whl", hash = "sha256:1f28b4522cdc2fb4256ac1a020c78acf9cba2c6b461ccd2c126f3aa8e8335d04"},
- {file = "attrs-23.1.0.tar.gz", hash = "sha256:6279836d581513a26f1bf235f9acd333bc9115683f14f7e8fae46c98fc50e015"},
-]
-
-[package.extras]
-cov = ["attrs[tests]", "coverage[toml] (>=5.3)"]
-dev = ["attrs[docs,tests]", "pre-commit"]
-docs = ["furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier", "zope-interface"]
-tests = ["attrs[tests-no-zope]", "zope-interface"]
-tests-no-zope = ["cloudpickle", "hypothesis", "mypy (>=1.1.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-
[[package]]
name = "av"
version = "11.0.0"
@@ -119,33 +91,33 @@ dev = ["freezegun (>=1.0,<2.0)", "pytest (>=6.0)", "pytest-cov"]
[[package]]
name = "black"
-version = "24.4.2"
+version = "24.10.0"
description = "The uncompromising code formatter."
optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
files = [
- {file = "black-24.4.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dd1b5a14e417189db4c7b64a6540f31730713d173f0b63e55fabd52d61d8fdce"},
- {file = "black-24.4.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8e537d281831ad0e71007dcdcbe50a71470b978c453fa41ce77186bbe0ed6021"},
- {file = "black-24.4.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eaea3008c281f1038edb473c1aa8ed8143a5535ff18f978a318f10302b254063"},
- {file = "black-24.4.2-cp310-cp310-win_amd64.whl", hash = "sha256:7768a0dbf16a39aa5e9a3ded568bb545c8c2727396d063bbaf847df05b08cd96"},
- {file = "black-24.4.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:257d724c2c9b1660f353b36c802ccece186a30accc7742c176d29c146df6e474"},
- {file = "black-24.4.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bdde6f877a18f24844e381d45e9947a49e97933573ac9d4345399be37621e26c"},
- {file = "black-24.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e151054aa00bad1f4e1f04919542885f89f5f7d086b8a59e5000e6c616896ffb"},
- {file = "black-24.4.2-cp311-cp311-win_amd64.whl", hash = "sha256:7e122b1c4fb252fd85df3ca93578732b4749d9be076593076ef4d07a0233c3e1"},
- {file = "black-24.4.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:accf49e151c8ed2c0cdc528691838afd217c50412534e876a19270fea1e28e2d"},
- {file = "black-24.4.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:88c57dc656038f1ab9f92b3eb5335ee9b021412feaa46330d5eba4e51fe49b04"},
- {file = "black-24.4.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:be8bef99eb46d5021bf053114442914baeb3649a89dc5f3a555c88737e5e98fc"},
- {file = "black-24.4.2-cp312-cp312-win_amd64.whl", hash = "sha256:415e686e87dbbe6f4cd5ef0fbf764af7b89f9057b97c908742b6008cc554b9c0"},
- {file = "black-24.4.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:bf10f7310db693bb62692609b397e8d67257c55f949abde4c67f9cc574492cc7"},
- {file = "black-24.4.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:98e123f1d5cfd42f886624d84464f7756f60ff6eab89ae845210631714f6db94"},
- {file = "black-24.4.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:48a85f2cb5e6799a9ef05347b476cce6c182d6c71ee36925a6c194d074336ef8"},
- {file = "black-24.4.2-cp38-cp38-win_amd64.whl", hash = "sha256:b1530ae42e9d6d5b670a34db49a94115a64596bc77710b1d05e9801e62ca0a7c"},
- {file = "black-24.4.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:37aae07b029fa0174d39daf02748b379399b909652a806e5708199bd93899da1"},
- {file = "black-24.4.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:da33a1a5e49c4122ccdfd56cd021ff1ebc4a1ec4e2d01594fef9b6f267a9e741"},
- {file = "black-24.4.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ef703f83fc32e131e9bcc0a5094cfe85599e7109f896fe8bc96cc402f3eb4b6e"},
- {file = "black-24.4.2-cp39-cp39-win_amd64.whl", hash = "sha256:b9176b9832e84308818a99a561e90aa479e73c523b3f77afd07913380ae2eab7"},
- {file = "black-24.4.2-py3-none-any.whl", hash = "sha256:d36ed1124bb81b32f8614555b34cc4259c3fbc7eec17870e8ff8ded335b58d8c"},
- {file = "black-24.4.2.tar.gz", hash = "sha256:c872b53057f000085da66a19c55d68f6f8ddcac2642392ad3a355878406fbd4d"},
+ {file = "black-24.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e6668650ea4b685440857138e5fe40cde4d652633b1bdffc62933d0db4ed9812"},
+ {file = "black-24.10.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:1c536fcf674217e87b8cc3657b81809d3c085d7bf3ef262ead700da345bfa6ea"},
+ {file = "black-24.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:649fff99a20bd06c6f727d2a27f401331dc0cc861fb69cde910fe95b01b5928f"},
+ {file = "black-24.10.0-cp310-cp310-win_amd64.whl", hash = "sha256:fe4d6476887de70546212c99ac9bd803d90b42fc4767f058a0baa895013fbb3e"},
+ {file = "black-24.10.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5a2221696a8224e335c28816a9d331a6c2ae15a2ee34ec857dcf3e45dbfa99ad"},
+ {file = "black-24.10.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f9da3333530dbcecc1be13e69c250ed8dfa67f43c4005fb537bb426e19200d50"},
+ {file = "black-24.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4007b1393d902b48b36958a216c20c4482f601569d19ed1df294a496eb366392"},
+ {file = "black-24.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:394d4ddc64782e51153eadcaaca95144ac4c35e27ef9b0a42e121ae7e57a9175"},
+ {file = "black-24.10.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b5e39e0fae001df40f95bd8cc36b9165c5e2ea88900167bddf258bacef9bbdc3"},
+ {file = "black-24.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d37d422772111794b26757c5b55a3eade028aa3fde43121ab7b673d050949d65"},
+ {file = "black-24.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:14b3502784f09ce2443830e3133dacf2c0110d45191ed470ecb04d0f5f6fcb0f"},
+ {file = "black-24.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:30d2c30dc5139211dda799758559d1b049f7f14c580c409d6ad925b74a4208a8"},
+ {file = "black-24.10.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:1cbacacb19e922a1d75ef2b6ccaefcd6e93a2c05ede32f06a21386a04cedb981"},
+ {file = "black-24.10.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:1f93102e0c5bb3907451063e08b9876dbeac810e7da5a8bfb7aeb5a9ef89066b"},
+ {file = "black-24.10.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ddacb691cdcdf77b96f549cf9591701d8db36b2f19519373d60d31746068dbf2"},
+ {file = "black-24.10.0-cp313-cp313-win_amd64.whl", hash = "sha256:680359d932801c76d2e9c9068d05c6b107f2584b2a5b88831c83962eb9984c1b"},
+ {file = "black-24.10.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:17374989640fbca88b6a448129cd1745c5eb8d9547b464f281b251dd00155ccd"},
+ {file = "black-24.10.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:63f626344343083322233f175aaf372d326de8436f5928c042639a4afbbf1d3f"},
+ {file = "black-24.10.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ccfa1d0cb6200857f1923b602f978386a3a2758a65b52e0950299ea014be6800"},
+ {file = "black-24.10.0-cp39-cp39-win_amd64.whl", hash = "sha256:2cd9c95431d94adc56600710f8813ee27eea544dd118d45896bb734e9d7a0dc7"},
+ {file = "black-24.10.0-py3-none-any.whl", hash = "sha256:3bb2b7a1f7b685f85b11fed1ef10f8a9148bceb49853e47a294a3dd963c1dd7d"},
+ {file = "black-24.10.0.tar.gz", hash = "sha256:846ea64c97afe3bc677b761787993be4991810ecc7a4a937816dd6bddedc4875"},
]
[package.dependencies]
@@ -159,7 +131,7 @@ typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
[package.extras]
colorama = ["colorama (>=0.4.3)"]
-d = ["aiohttp (>=3.7.4)", "aiohttp (>=3.7.4,!=3.9.0)"]
+d = ["aiohttp (>=3.10)"]
jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
uvloop = ["uvloop (>=0.15.2)"]
@@ -355,18 +327,18 @@ test = ["pytest (>=6)"]
[[package]]
name = "fastapi"
-version = "0.115.0"
+version = "0.115.6"
description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
optional = false
python-versions = ">=3.8"
files = [
- {file = "fastapi-0.115.0-py3-none-any.whl", hash = "sha256:17ea427674467486e997206a5ab25760f6b09e069f099b96f5b55a32fb6f1631"},
- {file = "fastapi-0.115.0.tar.gz", hash = "sha256:f93b4ca3529a8ebc6fc3fcf710e5efa8de3df9b41570958abf1d97d843138004"},
+ {file = "fastapi-0.115.6-py3-none-any.whl", hash = "sha256:e9240b29e36fa8f4bb7290316988e90c381e5092e0cbe84e7818cc3713bcf305"},
+ {file = "fastapi-0.115.6.tar.gz", hash = "sha256:9ec46f7addc14ea472958a96aae5b5de65f39721a46aaf5705c480d9a8b76654"},
]
[package.dependencies]
pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<2.0.0 || >2.0.0,<2.0.1 || >2.0.1,<2.1.0 || >2.1.0,<3.0.0"
-starlette = ">=0.37.2,<0.39.0"
+starlette = ">=0.40.0,<0.42.0"
typing-extensions = ">=4.8.0"
[package.extras]
@@ -375,21 +347,22 @@ standard = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.5)", "htt
[[package]]
name = "faster-whisper"
-version = "1.0.3"
+version = "1.1.0"
description = "Faster Whisper transcription with CTranslate2"
optional = false
python-versions = ">=3.8"
files = [
- {file = "faster-whisper-1.0.3.tar.gz", hash = "sha256:1a145db86450b56aaa623c8df7d4ef86e8a1159900f60533e2890e98e8453a17"},
- {file = "faster_whisper-1.0.3-py3-none-any.whl", hash = "sha256:364d0e378ab232ed26f39656e5c98548b38045224e206b20f7d8c90e2745b9d3"},
+ {file = "faster-whisper-1.1.0.tar.gz", hash = "sha256:cea4bba5d4527173fdbacafa56f2ffb17dd322688f6c3fdf5fd7b6b6c193ce17"},
+ {file = "faster_whisper-1.1.0-py3-none-any.whl", hash = "sha256:0f2d025676bbff1e46c4108b6f9a82578d6e33826c174af2990e45b33fab6182"},
]
[package.dependencies]
-av = ">=11.0,<13"
+av = ">=11"
ctranslate2 = ">=4.0,<5"
huggingface-hub = ">=0.13"
onnxruntime = ">=1.14,<2"
tokenizers = ">=0.13,<1"
+tqdm = "*"
[package.extras]
conversion = ["transformers[torch] (>=4.23)"]
@@ -478,56 +451,58 @@ files = [
[[package]]
name = "httptools"
-version = "0.5.0"
+version = "0.6.4"
description = "A collection of framework independent HTTP protocol utils."
optional = false
-python-versions = ">=3.5.0"
-files = [
- {file = "httptools-0.5.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:8f470c79061599a126d74385623ff4744c4e0f4a0997a353a44923c0b561ee51"},
- {file = "httptools-0.5.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e90491a4d77d0cb82e0e7a9cb35d86284c677402e4ce7ba6b448ccc7325c5421"},
- {file = "httptools-0.5.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c1d2357f791b12d86faced7b5736dea9ef4f5ecdc6c3f253e445ee82da579449"},
- {file = "httptools-0.5.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1f90cd6fd97c9a1b7fe9215e60c3bd97336742a0857f00a4cb31547bc22560c2"},
- {file = "httptools-0.5.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:5230a99e724a1bdbbf236a1b58d6e8504b912b0552721c7c6b8570925ee0ccde"},
- {file = "httptools-0.5.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:3a47a34f6015dd52c9eb629c0f5a8a5193e47bf2a12d9a3194d231eaf1bc451a"},
- {file = "httptools-0.5.0-cp310-cp310-win_amd64.whl", hash = "sha256:24bb4bb8ac3882f90aa95403a1cb48465de877e2d5298ad6ddcfdebec060787d"},
- {file = "httptools-0.5.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e67d4f8734f8054d2c4858570cc4b233bf753f56e85217de4dfb2495904cf02e"},
- {file = "httptools-0.5.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7e5eefc58d20e4c2da82c78d91b2906f1a947ef42bd668db05f4ab4201a99f49"},
- {file = "httptools-0.5.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0297822cea9f90a38df29f48e40b42ac3d48a28637368f3ec6d15eebefd182f9"},
- {file = "httptools-0.5.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:557be7fbf2bfa4a2ec65192c254e151684545ebab45eca5d50477d562c40f986"},
- {file = "httptools-0.5.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:54465401dbbec9a6a42cf737627fb0f014d50dc7365a6b6cd57753f151a86ff0"},
- {file = "httptools-0.5.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4d9ebac23d2de960726ce45f49d70eb5466725c0087a078866043dad115f850f"},
- {file = "httptools-0.5.0-cp311-cp311-win_amd64.whl", hash = "sha256:e8a34e4c0ab7b1ca17b8763613783e2458e77938092c18ac919420ab8655c8c1"},
- {file = "httptools-0.5.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:f659d7a48401158c59933904040085c200b4be631cb5f23a7d561fbae593ec1f"},
- {file = "httptools-0.5.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ef1616b3ba965cd68e6f759eeb5d34fbf596a79e84215eeceebf34ba3f61fdc7"},
- {file = "httptools-0.5.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3625a55886257755cb15194efbf209584754e31d336e09e2ffe0685a76cb4b60"},
- {file = "httptools-0.5.0-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:72ad589ba5e4a87e1d404cc1cb1b5780bfcb16e2aec957b88ce15fe879cc08ca"},
- {file = "httptools-0.5.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:850fec36c48df5a790aa735417dca8ce7d4b48d59b3ebd6f83e88a8125cde324"},
- {file = "httptools-0.5.0-cp36-cp36m-win_amd64.whl", hash = "sha256:f222e1e9d3f13b68ff8a835574eda02e67277d51631d69d7cf7f8e07df678c86"},
- {file = "httptools-0.5.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3cb8acf8f951363b617a8420768a9f249099b92e703c052f9a51b66342eea89b"},
- {file = "httptools-0.5.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:550059885dc9c19a072ca6d6735739d879be3b5959ec218ba3e013fd2255a11b"},
- {file = "httptools-0.5.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a04fe458a4597aa559b79c7f48fe3dceabef0f69f562daf5c5e926b153817281"},
- {file = "httptools-0.5.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7d0c1044bce274ec6711f0770fd2d5544fe392591d204c68328e60a46f88843b"},
- {file = "httptools-0.5.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c6eeefd4435055a8ebb6c5cc36111b8591c192c56a95b45fe2af22d9881eee25"},
- {file = "httptools-0.5.0-cp37-cp37m-win_amd64.whl", hash = "sha256:5b65be160adcd9de7a7e6413a4966665756e263f0d5ddeffde277ffeee0576a5"},
- {file = "httptools-0.5.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:fe9c766a0c35b7e3d6b6939393c8dfdd5da3ac5dec7f971ec9134f284c6c36d6"},
- {file = "httptools-0.5.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:85b392aba273566c3d5596a0a490978c085b79700814fb22bfd537d381dd230c"},
- {file = "httptools-0.5.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f5e3088f4ed33947e16fd865b8200f9cfae1144f41b64a8cf19b599508e096bc"},
- {file = "httptools-0.5.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8c2a56b6aad7cc8f5551d8e04ff5a319d203f9d870398b94702300de50190f63"},
- {file = "httptools-0.5.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:9b571b281a19762adb3f48a7731f6842f920fa71108aff9be49888320ac3e24d"},
- {file = "httptools-0.5.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:aa47ffcf70ba6f7848349b8a6f9b481ee0f7637931d91a9860a1838bfc586901"},
- {file = "httptools-0.5.0-cp38-cp38-win_amd64.whl", hash = "sha256:bede7ee075e54b9a5bde695b4fc8f569f30185891796b2e4e09e2226801d09bd"},
- {file = "httptools-0.5.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:64eba6f168803a7469866a9c9b5263a7463fa8b7a25b35e547492aa7322036b6"},
- {file = "httptools-0.5.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4b098e4bb1174096a93f48f6193e7d9aa7071506a5877da09a783509ca5fff42"},
- {file = "httptools-0.5.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9423a2de923820c7e82e18980b937893f4aa8251c43684fa1772e341f6e06887"},
- {file = "httptools-0.5.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ca1b7becf7d9d3ccdbb2f038f665c0f4857e08e1d8481cbcc1a86a0afcfb62b2"},
- {file = "httptools-0.5.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:50d4613025f15f4b11f1c54bbed4761c0020f7f921b95143ad6d58c151198142"},
- {file = "httptools-0.5.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8ffce9d81c825ac1deaa13bc9694c0562e2840a48ba21cfc9f3b4c922c16f372"},
- {file = "httptools-0.5.0-cp39-cp39-win_amd64.whl", hash = "sha256:1af91b3650ce518d226466f30bbba5b6376dbd3ddb1b2be8b0658c6799dd450b"},
- {file = "httptools-0.5.0.tar.gz", hash = "sha256:295874861c173f9101960bba332429bb77ed4dcd8cdf5cee9922eb00e4f6bc09"},
+python-versions = ">=3.8.0"
+files = [
+ {file = "httptools-0.6.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3c73ce323711a6ffb0d247dcd5a550b8babf0f757e86a52558fe5b86d6fefcc0"},
+ {file = "httptools-0.6.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:345c288418f0944a6fe67be8e6afa9262b18c7626c3ef3c28adc5eabc06a68da"},
+ {file = "httptools-0.6.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:deee0e3343f98ee8047e9f4c5bc7cedbf69f5734454a94c38ee829fb2d5fa3c1"},
+ {file = "httptools-0.6.4-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ca80b7485c76f768a3bc83ea58373f8db7b015551117375e4918e2aa77ea9b50"},
+ {file = "httptools-0.6.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:90d96a385fa941283ebd231464045187a31ad932ebfa541be8edf5b3c2328959"},
+ {file = "httptools-0.6.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:59e724f8b332319e2875efd360e61ac07f33b492889284a3e05e6d13746876f4"},
+ {file = "httptools-0.6.4-cp310-cp310-win_amd64.whl", hash = "sha256:c26f313951f6e26147833fc923f78f95604bbec812a43e5ee37f26dc9e5a686c"},
+ {file = "httptools-0.6.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:f47f8ed67cc0ff862b84a1189831d1d33c963fb3ce1ee0c65d3b0cbe7b711069"},
+ {file = "httptools-0.6.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:0614154d5454c21b6410fdf5262b4a3ddb0f53f1e1721cfd59d55f32138c578a"},
+ {file = "httptools-0.6.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f8787367fbdfccae38e35abf7641dafc5310310a5987b689f4c32cc8cc3ee975"},
+ {file = "httptools-0.6.4-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40b0f7fe4fd38e6a507bdb751db0379df1e99120c65fbdc8ee6c1d044897a636"},
+ {file = "httptools-0.6.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:40a5ec98d3f49904b9fe36827dcf1aadfef3b89e2bd05b0e35e94f97c2b14721"},
+ {file = "httptools-0.6.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:dacdd3d10ea1b4ca9df97a0a303cbacafc04b5cd375fa98732678151643d4988"},
+ {file = "httptools-0.6.4-cp311-cp311-win_amd64.whl", hash = "sha256:288cd628406cc53f9a541cfaf06041b4c71d751856bab45e3702191f931ccd17"},
+ {file = "httptools-0.6.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:df017d6c780287d5c80601dafa31f17bddb170232d85c066604d8558683711a2"},
+ {file = "httptools-0.6.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:85071a1e8c2d051b507161f6c3e26155b5c790e4e28d7f236422dbacc2a9cc44"},
+ {file = "httptools-0.6.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69422b7f458c5af875922cdb5bd586cc1f1033295aa9ff63ee196a87519ac8e1"},
+ {file = "httptools-0.6.4-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:16e603a3bff50db08cd578d54f07032ca1631450ceb972c2f834c2b860c28ea2"},
+ {file = "httptools-0.6.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ec4f178901fa1834d4a060320d2f3abc5c9e39766953d038f1458cb885f47e81"},
+ {file = "httptools-0.6.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:f9eb89ecf8b290f2e293325c646a211ff1c2493222798bb80a530c5e7502494f"},
+ {file = "httptools-0.6.4-cp312-cp312-win_amd64.whl", hash = "sha256:db78cb9ca56b59b016e64b6031eda5653be0589dba2b1b43453f6e8b405a0970"},
+ {file = "httptools-0.6.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ade273d7e767d5fae13fa637f4d53b6e961fb7fd93c7797562663f0171c26660"},
+ {file = "httptools-0.6.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:856f4bc0478ae143bad54a4242fccb1f3f86a6e1be5548fecfd4102061b3a083"},
+ {file = "httptools-0.6.4-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:322d20ea9cdd1fa98bd6a74b77e2ec5b818abdc3d36695ab402a0de8ef2865a3"},
+ {file = "httptools-0.6.4-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4d87b29bd4486c0093fc64dea80231f7c7f7eb4dc70ae394d70a495ab8436071"},
+ {file = "httptools-0.6.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:342dd6946aa6bda4b8f18c734576106b8a31f2fe31492881a9a160ec84ff4bd5"},
+ {file = "httptools-0.6.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4b36913ba52008249223042dca46e69967985fb4051951f94357ea681e1f5dc0"},
+ {file = "httptools-0.6.4-cp313-cp313-win_amd64.whl", hash = "sha256:28908df1b9bb8187393d5b5db91435ccc9c8e891657f9cbb42a2541b44c82fc8"},
+ {file = "httptools-0.6.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:d3f0d369e7ffbe59c4b6116a44d6a8eb4783aae027f2c0b366cf0aa964185dba"},
+ {file = "httptools-0.6.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:94978a49b8f4569ad607cd4946b759d90b285e39c0d4640c6b36ca7a3ddf2efc"},
+ {file = "httptools-0.6.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40dc6a8e399e15ea525305a2ddba998b0af5caa2566bcd79dcbe8948181eeaff"},
+ {file = "httptools-0.6.4-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ab9ba8dcf59de5181f6be44a77458e45a578fc99c31510b8c65b7d5acc3cf490"},
+ {file = "httptools-0.6.4-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:fc411e1c0a7dcd2f902c7c48cf079947a7e65b5485dea9decb82b9105ca71a43"},
+ {file = "httptools-0.6.4-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:d54efd20338ac52ba31e7da78e4a72570cf729fac82bc31ff9199bedf1dc7440"},
+ {file = "httptools-0.6.4-cp38-cp38-win_amd64.whl", hash = "sha256:df959752a0c2748a65ab5387d08287abf6779ae9165916fe053e68ae1fbdc47f"},
+ {file = "httptools-0.6.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:85797e37e8eeaa5439d33e556662cc370e474445d5fab24dcadc65a8ffb04003"},
+ {file = "httptools-0.6.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:db353d22843cf1028f43c3651581e4bb49374d85692a85f95f7b9a130e1b2cab"},
+ {file = "httptools-0.6.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d1ffd262a73d7c28424252381a5b854c19d9de5f56f075445d33919a637e3547"},
+ {file = "httptools-0.6.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:703c346571fa50d2e9856a37d7cd9435a25e7fd15e236c397bf224afaa355fe9"},
+ {file = "httptools-0.6.4-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:aafe0f1918ed07b67c1e838f950b1c1fabc683030477e60b335649b8020e1076"},
+ {file = "httptools-0.6.4-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:0e563e54979e97b6d13f1bbc05a96109923e76b901f786a5eae36e99c01237bd"},
+ {file = "httptools-0.6.4-cp39-cp39-win_amd64.whl", hash = "sha256:b799de31416ecc589ad79dd85a0b2657a8fe39327944998dea368c1d4c9e55e6"},
+ {file = "httptools-0.6.4.tar.gz", hash = "sha256:4e93eee4add6493b59a5c514da98c939b244fce4a0d8879cd3f466562f4b7d5c"},
]
[package.extras]
-test = ["Cython (>=0.29.24,<0.30.0)"]
+test = ["Cython (>=0.29.24)"]
[[package]]
name = "huggingface-hub"
@@ -739,13 +714,13 @@ files = [
[[package]]
name = "mkdocs"
-version = "1.6.0"
+version = "1.6.1"
description = "Project documentation with Markdown."
optional = false
python-versions = ">=3.8"
files = [
- {file = "mkdocs-1.6.0-py3-none-any.whl", hash = "sha256:1eb5cb7676b7d89323e62b56235010216319217d4af5ddc543a91beb8d125ea7"},
- {file = "mkdocs-1.6.0.tar.gz", hash = "sha256:a73f735824ef83a4f3bcb7a231dcab23f5a838f88b7efc54a0eef5fbdbc3c512"},
+ {file = "mkdocs-1.6.1-py3-none-any.whl", hash = "sha256:db91759624d1647f3f34aa0c3f327dd2601beae39a366d6e064c03468d35c20e"},
+ {file = "mkdocs-1.6.1.tar.gz", hash = "sha256:7b432f01d928c084353ab39c57282f29f92136665bdd6abf7c1ec8d822ef86f2"},
]
[package.dependencies]
@@ -785,13 +760,13 @@ pyyaml = ">=5.1"
[[package]]
name = "mkdocs-material"
-version = "9.5.27"
+version = "9.5.49"
description = "Documentation that simply works"
optional = false
python-versions = ">=3.8"
files = [
- {file = "mkdocs_material-9.5.27-py3-none-any.whl", hash = "sha256:af8cc263fafa98bb79e9e15a8c966204abf15164987569bd1175fd66a7705182"},
- {file = "mkdocs_material-9.5.27.tar.gz", hash = "sha256:a7d4a35f6d4a62b0c43a0cfe7e987da0980c13587b5bc3c26e690ad494427ec0"},
+ {file = "mkdocs_material-9.5.49-py3-none-any.whl", hash = "sha256:c3c2d8176b18198435d3a3e119011922f3e11424074645c24019c2dcf08a360e"},
+ {file = "mkdocs_material-9.5.49.tar.gz", hash = "sha256:3671bb282b4f53a1c72e08adbe04d2481a98f85fed392530051f80ff94a9621d"},
]
[package.dependencies]
@@ -1052,13 +1027,13 @@ type = ["mypy (>=1.8)"]
[[package]]
name = "pluggy"
-version = "1.0.0"
+version = "1.5.0"
description = "plugin and hook calling mechanisms for python"
optional = false
-python-versions = ">=3.6"
+python-versions = ">=3.8"
files = [
- {file = "pluggy-1.0.0-py2.py3-none-any.whl", hash = "sha256:74134bbf457f031a36d68416e1509f34bd5ccc019f0bcc952c7b909d06b37bd3"},
- {file = "pluggy-1.0.0.tar.gz", hash = "sha256:4224373bacce55f955a878bf9cfa763c1e360858e330072059e10bad68531159"},
+ {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"},
+ {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"},
]
[package.extras]
@@ -1087,17 +1062,6 @@ files = [
{file = "protobuf-4.22.3.tar.gz", hash = "sha256:23452f2fdea754a8251d0fc88c0317735ae47217e0d27bf330a30eec2848811a"},
]
-[[package]]
-name = "py"
-version = "1.11.0"
-description = "library with cross-python path, ini-parsing, io, code, log facilities"
-optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
-files = [
- {file = "py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378"},
- {file = "py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719"},
-]
-
[[package]]
name = "pydantic"
version = "1.10.7"
@@ -1166,13 +1130,13 @@ windows-terminal = ["colorama (>=0.4.6)"]
[[package]]
name = "pymdown-extensions"
-version = "10.8.1"
+version = "10.12"
description = "Extension pack for Python Markdown."
optional = false
python-versions = ">=3.8"
files = [
- {file = "pymdown_extensions-10.8.1-py3-none-any.whl", hash = "sha256:f938326115884f48c6059c67377c46cf631c733ef3629b6eed1349989d1b30cb"},
- {file = "pymdown_extensions-10.8.1.tar.gz", hash = "sha256:3ab1db5c9e21728dabf75192d71471f8e50f216627e9a1fa9535ecb0231b9940"},
+ {file = "pymdown_extensions-10.12-py3-none-any.whl", hash = "sha256:49f81412242d3527b8b4967b990df395c89563043bc51a3d2d7d500e52123b77"},
+ {file = "pymdown_extensions-10.12.tar.gz", hash = "sha256:b0ee1e0b2bef1071a47891ab17003bfe5bf824a398e13f49f8ed653b699369a7"},
]
[package.dependencies]
@@ -1195,27 +1159,25 @@ files = [
[[package]]
name = "pytest"
-version = "6.2.5"
+version = "8.3.4"
description = "pytest: simple powerful testing with Python"
optional = false
-python-versions = ">=3.6"
+python-versions = ">=3.8"
files = [
- {file = "pytest-6.2.5-py3-none-any.whl", hash = "sha256:7310f8d27bc79ced999e760ca304d69f6ba6c6649c0b60fb0e04a4a77cacc134"},
- {file = "pytest-6.2.5.tar.gz", hash = "sha256:131b36680866a76e6781d13f101efb86cf674ebb9762eb70d3082b6f29889e89"},
+ {file = "pytest-8.3.4-py3-none-any.whl", hash = "sha256:50e16d954148559c9a74109af1eaf0c945ba2d8f30f0a3d3335edde19788b6f6"},
+ {file = "pytest-8.3.4.tar.gz", hash = "sha256:965370d062bce11e73868e0335abac31b4d3de0e82f4007408d242b4f8610761"},
]
[package.dependencies]
-atomicwrites = {version = ">=1.0", markers = "sys_platform == \"win32\""}
-attrs = ">=19.2.0"
colorama = {version = "*", markers = "sys_platform == \"win32\""}
+exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
iniconfig = "*"
packaging = "*"
-pluggy = ">=0.12,<2.0"
-py = ">=1.8.2"
-toml = "*"
+pluggy = ">=1.5,<2"
+tomli = {version = ">=1", markers = "python_version < \"3.11\""}
[package.extras]
-testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "requests", "xmlschema"]
+dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
[[package]]
name = "python-dateutil"
@@ -1247,13 +1209,13 @@ cli = ["click (>=5.0)"]
[[package]]
name = "python-multipart"
-version = "0.0.12"
+version = "0.0.20"
description = "A streaming multipart parser for Python"
optional = false
python-versions = ">=3.8"
files = [
- {file = "python_multipart-0.0.12-py3-none-any.whl", hash = "sha256:43dcf96cf65888a9cd3423544dd0d75ac10f7aa0c3c28a175bbcd00c9ce1aebf"},
- {file = "python_multipart-0.0.12.tar.gz", hash = "sha256:045e1f98d719c1ce085ed7f7e1ef9d8ccc8c02ba02b5566d5f7521410ced58cb"},
+ {file = "python_multipart-0.0.20-py3-none-any.whl", hash = "sha256:8a62d3a8335e06589fe01f2a3e178cdcc632f3fbe0d492ad9ee0ec35aab1f104"},
+ {file = "python_multipart-0.0.20.tar.gz", hash = "sha256:8dd0cab45b8e23064ae09147625994d090fa46f5b0d1e13af944c331a7fa9d13"},
]
[[package]]
@@ -1411,29 +1373,29 @@ use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]]
name = "ruff"
-version = "0.5.0"
+version = "0.8.3"
description = "An extremely fast Python linter and code formatter, written in Rust."
optional = false
python-versions = ">=3.7"
files = [
- {file = "ruff-0.5.0-py3-none-linux_armv6l.whl", hash = "sha256:ee770ea8ab38918f34e7560a597cc0a8c9a193aaa01bfbd879ef43cb06bd9c4c"},
- {file = "ruff-0.5.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:38f3b8327b3cb43474559d435f5fa65dacf723351c159ed0dc567f7ab735d1b6"},
- {file = "ruff-0.5.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:7594f8df5404a5c5c8f64b8311169879f6cf42142da644c7e0ba3c3f14130370"},
- {file = "ruff-0.5.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:adc7012d6ec85032bc4e9065110df205752d64010bed5f958d25dbee9ce35de3"},
- {file = "ruff-0.5.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d505fb93b0fabef974b168d9b27c3960714d2ecda24b6ffa6a87ac432905ea38"},
- {file = "ruff-0.5.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9dc5cfd3558f14513ed0d5b70ce531e28ea81a8a3b1b07f0f48421a3d9e7d80a"},
- {file = "ruff-0.5.0-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:db3ca35265de239a1176d56a464b51557fce41095c37d6c406e658cf80bbb362"},
- {file = "ruff-0.5.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b1a321c4f68809fddd9b282fab6a8d8db796b270fff44722589a8b946925a2a8"},
- {file = "ruff-0.5.0-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2c4dfcd8d34b143916994b3876b63d53f56724c03f8c1a33a253b7b1e6bf2a7d"},
- {file = "ruff-0.5.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:81e5facfc9f4a674c6a78c64d38becfbd5e4f739c31fcd9ce44c849f1fad9e4c"},
- {file = "ruff-0.5.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:e589e27971c2a3efff3fadafb16e5aef7ff93250f0134ec4b52052b673cf988d"},
- {file = "ruff-0.5.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:d2ffbc3715a52b037bcb0f6ff524a9367f642cdc5817944f6af5479bbb2eb50e"},
- {file = "ruff-0.5.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:cd096e23c6a4f9c819525a437fa0a99d1c67a1b6bb30948d46f33afbc53596cf"},
- {file = "ruff-0.5.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:46e193b36f2255729ad34a49c9a997d506e58f08555366b2108783b3064a0e1e"},
- {file = "ruff-0.5.0-py3-none-win32.whl", hash = "sha256:49141d267100f5ceff541b4e06552e98527870eafa1acc9dec9139c9ec5af64c"},
- {file = "ruff-0.5.0-py3-none-win_amd64.whl", hash = "sha256:e9118f60091047444c1b90952736ee7b1792910cab56e9b9a9ac20af94cd0440"},
- {file = "ruff-0.5.0-py3-none-win_arm64.whl", hash = "sha256:ed5c4df5c1fb4518abcb57725b576659542bdbe93366f4f329e8f398c4b71178"},
- {file = "ruff-0.5.0.tar.gz", hash = "sha256:eb641b5873492cf9bd45bc9c5ae5320648218e04386a5f0c264ad6ccce8226a1"},
+ {file = "ruff-0.8.3-py3-none-linux_armv6l.whl", hash = "sha256:8d5d273ffffff0acd3db5bf626d4b131aa5a5ada1276126231c4174543ce20d6"},
+ {file = "ruff-0.8.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:e4d66a21de39f15c9757d00c50c8cdd20ac84f55684ca56def7891a025d7e939"},
+ {file = "ruff-0.8.3-py3-none-macosx_11_0_arm64.whl", hash = "sha256:c356e770811858bd20832af696ff6c7e884701115094f427b64b25093d6d932d"},
+ {file = "ruff-0.8.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c0a60a825e3e177116c84009d5ebaa90cf40dfab56e1358d1df4e29a9a14b13"},
+ {file = "ruff-0.8.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:75fb782f4db39501210ac093c79c3de581d306624575eddd7e4e13747e61ba18"},
+ {file = "ruff-0.8.3-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7f26bc76a133ecb09a38b7868737eded6941b70a6d34ef53a4027e83913b6502"},
+ {file = "ruff-0.8.3-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:01b14b2f72a37390c1b13477c1c02d53184f728be2f3ffc3ace5b44e9e87b90d"},
+ {file = "ruff-0.8.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:53babd6e63e31f4e96ec95ea0d962298f9f0d9cc5990a1bbb023a6baf2503a82"},
+ {file = "ruff-0.8.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1ae441ce4cf925b7f363d33cd6570c51435972d697e3e58928973994e56e1452"},
+ {file = "ruff-0.8.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7c65bc0cadce32255e93c57d57ecc2cca23149edd52714c0c5d6fa11ec328cd"},
+ {file = "ruff-0.8.3-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:5be450bb18f23f0edc5a4e5585c17a56ba88920d598f04a06bd9fd76d324cb20"},
+ {file = "ruff-0.8.3-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:8faeae3827eaa77f5721f09b9472a18c749139c891dbc17f45e72d8f2ca1f8fc"},
+ {file = "ruff-0.8.3-py3-none-musllinux_1_2_i686.whl", hash = "sha256:db503486e1cf074b9808403991663e4277f5c664d3fe237ee0d994d1305bb060"},
+ {file = "ruff-0.8.3-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:6567be9fb62fbd7a099209257fef4ad2c3153b60579818b31a23c886ed4147ea"},
+ {file = "ruff-0.8.3-py3-none-win32.whl", hash = "sha256:19048f2f878f3ee4583fc6cb23fb636e48c2635e30fb2022b3a1cd293402f964"},
+ {file = "ruff-0.8.3-py3-none-win_amd64.whl", hash = "sha256:f7df94f57d7418fa7c3ffb650757e0c2b96cf2501a0b192c18e4fb5571dfada9"},
+ {file = "ruff-0.8.3-py3-none-win_arm64.whl", hash = "sha256:fe2756edf68ea79707c8d68b78ca9a58ed9af22e430430491ee03e718b5e4936"},
+ {file = "ruff-0.8.3.tar.gz", hash = "sha256:5e7558304353b84279042fc584a4f4cb8a07ae79b2bf3da1a7551d960b5626d3"},
]
[[package]]
@@ -1476,13 +1438,13 @@ files = [
[[package]]
name = "starlette"
-version = "0.37.2"
+version = "0.41.3"
description = "The little ASGI library that shines."
optional = false
python-versions = ">=3.8"
files = [
- {file = "starlette-0.37.2-py3-none-any.whl", hash = "sha256:6fe59f29268538e5d0d182f2791a479a0c64638e6935d1c6989e63fb2699c6ee"},
- {file = "starlette-0.37.2.tar.gz", hash = "sha256:9af890290133b79fc3db55474ade20f6220a364a0402e0b556e7cd5e1e093823"},
+ {file = "starlette-0.41.3-py3-none-any.whl", hash = "sha256:44cedb2b7c77a9de33a8b74b2b90e9f50d11fcf25d8270ea525ad71a25374ff7"},
+ {file = "starlette-0.41.3.tar.gz", hash = "sha256:0e4ab3d16522a255be6b28260b938eae2482f98ce5cc934cb08dce8dc3ba5835"},
]
[package.dependencies]
@@ -1604,17 +1566,6 @@ dev = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"]
testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
-[[package]]
-name = "toml"
-version = "0.10.2"
-description = "Python Library for Tom's Obvious, Minimal Language"
-optional = false
-python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
-files = [
- {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
- {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
-]
-
[[package]]
name = "tomli"
version = "2.0.1"
@@ -1728,20 +1679,21 @@ url = "https://download.pytorch.org/whl/cpu/torch-1.13.1%2Bcpu-cp310-cp310-win_a
[[package]]
name = "tqdm"
-version = "4.66.5"
+version = "4.67.1"
description = "Fast, Extensible Progress Meter"
optional = false
python-versions = ">=3.7"
files = [
- {file = "tqdm-4.66.5-py3-none-any.whl", hash = "sha256:90279a3770753eafc9194a0364852159802111925aa30eb3f9d85b0e805ac7cd"},
- {file = "tqdm-4.66.5.tar.gz", hash = "sha256:e1020aef2e5096702d8a025ac7d16b1577279c9d63f8375b63083e9a5f0fcbad"},
+ {file = "tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2"},
+ {file = "tqdm-4.67.1.tar.gz", hash = "sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2"},
]
[package.dependencies]
colorama = {version = "*", markers = "platform_system == \"Windows\""}
[package.extras]
-dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
+dev = ["nbval", "pytest (>=6)", "pytest-asyncio (>=0.24)", "pytest-cov", "pytest-timeout"]
+discord = ["requests"]
notebook = ["ipywidgets (>=6)"]
slack = ["slack-sdk"]
telegram = ["requests"]
@@ -1775,20 +1727,20 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
[[package]]
name = "uvicorn"
-version = "0.31.0"
+version = "0.34.0"
description = "The lightning-fast ASGI server."
optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
files = [
- {file = "uvicorn-0.31.0-py3-none-any.whl", hash = "sha256:cac7be4dd4d891c363cd942160a7b02e69150dcbc7a36be04d5f4af4b17c8ced"},
- {file = "uvicorn-0.31.0.tar.gz", hash = "sha256:13bc21373d103859f68fe739608e2eb054a816dea79189bc3ca08ea89a275906"},
+ {file = "uvicorn-0.34.0-py3-none-any.whl", hash = "sha256:023dc038422502fa28a09c7a30bf2b6991512da7dcdb8fd35fe57cfc154126f4"},
+ {file = "uvicorn-0.34.0.tar.gz", hash = "sha256:404051050cd7e905de2c9a7e61790943440b3416f49cb409f965d9dcd0fa73e9"},
]
[package.dependencies]
click = ">=7.0"
colorama = {version = ">=0.4", optional = true, markers = "sys_platform == \"win32\" and extra == \"standard\""}
h11 = ">=0.8"
-httptools = {version = ">=0.5.0", optional = true, markers = "extra == \"standard\""}
+httptools = {version = ">=0.6.3", optional = true, markers = "extra == \"standard\""}
python-dotenv = {version = ">=0.13", optional = true, markers = "extra == \"standard\""}
pyyaml = {version = ">=5.1", optional = true, markers = "extra == \"standard\""}
typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
@@ -1797,7 +1749,7 @@ watchfiles = {version = ">=0.13", optional = true, markers = "extra == \"standar
websockets = {version = ">=10.4", optional = true, markers = "extra == \"standard\""}
[package.extras]
-standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
+standard = ["colorama (>=0.4)", "httptools (>=0.6.3)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
[[package]]
name = "uvloop"
@@ -2003,4 +1955,4 @@ files = [
[metadata]
lock-version = "2.0"
python-versions = "^3.10"
-content-hash = "3a007512112802c1d81dea2788a1e5523f701cf84ba97a163e7ac1882707e119"
+content-hash = "ecee871583f0f6a382aa54e3d56027ca899b86784b1ba5a119930f52a3beb7c3"
diff --git a/pyproject.toml b/pyproject.toml
index a362775ec32cecbda731eb076174bbc9b81a5877..230382e0573c6e264ea16d28e02c6bb46a5d2806 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -18,15 +18,15 @@ priority = "explicit"
[tool.poetry.dependencies]
python = "^3.10"
-uvicorn = { extras = ["standard"], version = "^0.31.0" }
-tqdm = "^4.66.5"
-python-multipart = "^0.0.12"
+uvicorn = { extras = ["standard"], version = "^0.34.0" }
+tqdm = "^4.67.1"
+python-multipart = "^0.0.20"
ffmpeg-python = "^0.2.0"
-fastapi = "^0.115.0"
+fastapi = "^0.115.6"
llvmlite = "^0.43.0"
numba = "^0.60.0"
openai-whisper = "^20240930"
-faster-whisper = "^1.0.3"
+faster-whisper = "^1.1.0"
torch = [
{ markers = "sys_platform == 'darwin' and platform_machine == 'arm64'", url = "https://download.pytorch.org/whl/cpu/torch-1.13.1-cp310-none-macosx_11_0_arm64.whl" },
{ markers = "sys_platform == 'linux' and platform_machine == 'arm64'", url = "https://download.pytorch.org/whl/cpu/torch-1.13.1-cp310-none-macosx_11_0_arm64.whl" },
@@ -37,12 +37,12 @@ torch = [
]
[tool.poetry.dev-dependencies]
-pytest = "^6.2.5"
-ruff = "^0.5.0"
-black = "^24.4.2"
-mkdocs = "^1.6.0"
-mkdocs-material = "^9.5.27"
-pymdown-extensions = "^10.8.1"
+pytest = "^8.3.4"
+ruff = "^0.8.3"
+black = "^24.10.0"
+mkdocs = "^1.6.1"
+mkdocs-material = "^9.5.49"
+pymdown-extensions = "^10.12"
[build-system]
requires = ["poetry-core>=1.0.0"]