CoolFace
Modelpublic

deAPI-ai/whisper-large-v3-ct2

sourceHugging Faceotherupdated 2mo agoView on Hugging Face
0likes74downloads
Model Card

Whisper Large V3 CT2 — Word/Char Timestamps + Diarization Bundle

A single, self-contained ASR bundle: faster-whisper / CTranslate2 transcription of Whisper large-v3, plus wav2vec2 forced alignment for accurate per-word and per-char timestamps, plus optional pyannote speaker diarization. Everything is resolved locally from this directory — nothing is downloaded at runtime.

Contents

PathComponentPurpose
/Whisper large-v3 (CTranslate2, int8_float16-ready)transcription engine
aligners/enwav2vec2-large-xlsr-53-englishEnglish word/char timestamps
aligners/plwav2vec2-large-xlsr-53-polishPolish word/char timestamps
aligners/multiwav2vec2-xlsr-multilingual-5656-language fallback aligner
diarization/speaker-diarization-community-1speaker labels (who spoke when)

Licenses

This is a bundle of independently-licensed models. Each component keeps its own license:

ComponentSourceLicense
Whisper large-v3 weightsopenai/whisper-large-v3MIT
CTranslate2 conversion formatOpenNMT/CTranslate2 (SYSTRAN)MIT
English alignerjonatasgrosman/wav2vec2-large-xlsr-53-englishApache-2.0
Polish alignerjonatasgrosman/wav2vec2-large-xlsr-53-polishApache-2.0
Multilingual alignervoidful/wav2vec2-xlsr-multilingual-56Apache-2.0
Diarizationpyannote/speaker-diarization-community-1CC-BY-4.0 (weights) · pyannote.audio code MIT

Attribution (required): the diarization weights are licensed CC-BY-4.0 — commercial use is permitted with attribution to pyannote (Hervé Bredin et al.) and the speaker-diarization-community-1 model card. Keep this notice on any redistribution.

The bundle is made available by deAPI-ai on Hugging Face, configured for integration with GamerHash AI's platform. All credit for the underlying models belongs to their respective creators listed above.

Note on file formats

  • —model.bin is CTranslate2's own binary format (the transcription engine) — not a PyTorch pickle.
  • —The aligners are stored as safetensors.
  • —diarization/*/pytorch_model.bin are pyannote / PyTorch-Lightning checkpoints; they carry non-tensor hyperparameters that safetensors cannot hold, so they remain .bin (identical to the official pyannote/speaker-diarization-community-1 repo).