diff --git a/CHANGELOG.md b/CHANGELOG.md index 9c8c9c4f727866d006c3374d629e7881e94d7d84..c9d3481438d2dcf62ee5efe122373c4c2b69bb32 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,10 @@ Changelog Unreleased ---------- +### Added + + - Set mel generation to adjust n_dims automatically to match the loaded model + [1.6.0] (2024-10-06) -------------------- diff --git a/app/openai_whisper/core.py b/app/openai_whisper/core.py index 88bde4f2b20f8a91887d5dbdc7ca049cc58d39d9..e93f5ff3d05ead22704e7aeec3cb9435dc25ddad 100644 --- a/app/openai_whisper/core.py +++ b/app/openai_whisper/core.py @@ -48,7 +48,7 @@ def language_detection(audio): 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).to(model.device) + mel = whisper.log_mel_spectrogram(audio, model.dims.n_mels).to(model.device) # detect the spoken language with model_lock: