Speaker-Labeled Transcription With Whisper Diarization
Whisper Diarization is the who-said-what option in our speech-to-text API comparison, combining transcription and speaker labels in one call.
⚡️ Blazing fast audio transcription with speaker diarization | Whisper Large V3 Turbo & pyannote 4.0 community-1 | word & sentence level timestamps | prompt
"LLama, AI, Meta."
{
"file": "https://replicate.delivery/pbxt/JcL0ttZLlbchC0tL9ZtB20phzeXCSuMm0EJNdLYElgILoZci/AI%20should%20be%20open-sourced.mp3",
"prompt": "LLama, AI, Meta.",
"file_url": "",
"language": "en",
"translate": false,
"num_speakers": 2
}
/src/predict.py:233: UserWarning: torchaudio._backend.utils.info has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release. metadata = torchaudio.info(str(path)) /root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/torchaudio/_backend/ffmpeg.py:20: UserWarning: torio.io._streaming_media_decoder.StreamingMediaDecoder has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release. s = torchaudio.io.StreamReader(src, format, None, buffer_size) /root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/torchaudio/_backend/ffmpeg.py:27: UserWarning: torchaudio._backend.common.AudioMetaData has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release. return AudioMetaData( INFO:predict:Audio metadata: sample_rate=44100, num_channels=2, num_frames=66473984, bits_per_sample=0, encoding=MP3 INFO:predict:Audio normalized in 3.02s INFO:predict:Audio duration: 1507.35s INFO:predict:GPU type: NVIDIA L40S INFO:predict:Starting transcription INFO:faster_whisper:Processing audio with duration 25:07.347 INFO:faster_whisper:VAD filter removed 00:37.899 of audio INFO:predict:Transcription completed in 28.72s. Detected language: en. Segments: 908 INFO:predict:Starting diarization /root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/torchaudio/_backend/utils.py:213: UserWarning: In 2.9, this function's implementation will be changed to use torchaudio.load_with_torchcodec` under the hood. Some parameters like ``normalize``, ``format``, ``buffer_size``, and ``backend`` will be ignored. We recommend that you port your code to rely directly on TorchCodec's decoder instead: https://docs.pytorch.org/torchcodec/stable/generated/torchcodec.decoders.AudioDecoder.html#torchcodec.decoders.AudioDecoder. warnings.warn( /root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/torchaudio/_backend/ffmpeg.py:88: UserWarning: torio.io._streaming_media_decoder.StreamingMediaDecoder has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release. s = torchaudio.io.StreamReader(src, format, None, buffer_size) /root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/pyannote/audio/utils/reproducibility.py:74: ReproducibilityWarning: TensorFloat-32 (TF32) has been disabled as it might lead to reproducibility issues and lower accuracy. It can be re-enabled by calling >>> import torch >>> torch.backends.cuda.matmul.allow_tf32 = True >>> torch.backends.cudnn.allow_tf32 = True See https://github.com/pyannote/pyannote-audio/issues/1370 for more details. warnings.warn( /root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/pyannote/audio/models/blocks/pooling.py:103: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at /pytorch/aten/src/ATen/native/ReduceOps.cpp:1839.) std = sequences.std(dim=-1, correction=1) INFO:predict:Diarization completed in 15.41s. Detected speakers: 2 INFO:predict:Starting segment reconciliation INFO:predict:Segment reconciliation completed in 2.45s. Final segments: 217 INFO:predict:Run completed in 51.31s
744c4f2bffae674f82e79ed46f9cc54796d4903b3e20e68353e05a93eb10a55c