What's Changed only merge when clip_timestamps are not provided by @MahmoudAshraf97 in #1345 Fix: Prevent <|nocaptions|> tokens in BatchedInferencePipeline by @mmichelli in #1338 Upgrade to Silero-VAD V6 by @MahmoudAshraf97 and @sssshhhhhh in #1373 Offload retry logic to hf hub by @MahmoudAshraf97 in #1382 Refinements for clip timestamps in batched inference by @MahmoudAshraf97 in #1376 New Contri…
What's Changed feat: allow passing specific revision to download by @felixmosh in #1292 Support distil-large-v3.5 by @MahmoudAshraf97 in #1311 Feature: Allow loading of private HF models by @r15hil in #1309 bugfix: Get correct chunk index when restoring timestamps by @MahmoudAshraf97 in #1336 Remove Silence in Batched transcription by @MahmoudAshraf97 in #1297 New Contributors @djpg made their fir…
What's Changed Brings back original VAD parameters naming by @Purfview in #1181 Make batched suppress_tokens behaviour same as in sequential by @Purfview in #1194 Fixes OOM Errors - too high RAM usage by VAD by @Purfview in #1198 Add duration of audio and VAD removed duration to BatchedInferencePipeline by @greenw0lf in #1186 Fix neg_threshold by @Purfview in #1191 New Contributors @greenw0lf made…
New Features New batched inference that is 4x faster and accurate, Refer to README on usage instructions. Support for the new large-v3-turbo model. VAD filter is now 3x faster on CPU. Feature Extraction is now 3x faster. Added log_progress to WhisperModel.transcribe to print transcription progress. Added multilingual option to transcription to allow transcribing multilingual audio. Note that Large…
Upgrade Silero-Vad model to latest V5 version (#884) Silero-vad V5 release: https://github.com/snakers4/silero-vad/releases/tag/v5.0 window_size_samples parameter is fixed at 512. Change to use the state variable instead of the existing h and c variables. Slightly changed internal logic, now some context (part of previous chunk) is passed along with the current chunk. Change the dimensions of the…
Add support for distil-large-v3 (#755) The latest Distil-Whisper model, distil-large-v3, is intrinsically designed to work with the OpenAI sequential algorithm. Benchmarks (#773) Introduces functionality to measure benchmarking for memory, Word Error Rate (WER), and speed in Faster-whisper. Support initializing more whisper model args (#807) Small bug fix: code breaks if audio is empty (#768) Fool…
Bug fixes and performance improvements: Update logic to get segment from features before encoding (#705) Fix window end heuristic for hallucination_silence_threshold (#706)
Fix the broken tag v0.10.0
Support "large-v3" model with The ability to load feature_size/num_mels and other from preprocessor_config.json A new language token for Cantonese (yue) Update CTranslate2 requirement to include the latest version 3.22.0 Update tokenizers requirement to include the latest version 0.15 Change the hub to fetch models from Systran organization
Support distil-whisper model (#557) Robust knowledge distillation of the Whisper model via large-scale pseudo-labelling. For more detail: https://github.com/huggingface/distil-whisper Upgrade ctranslate2 version to 4.0 to support CUDA 12 (#694) Upgrade PyAV version to 11.* to support Python3.12.x (#679) Small bug fixes Illogical "Avoid computing higher temperatures on no_speech" (#652) broken prom…