Mahmoud Ashraf c26d609974 only merge when clip_timestamps are not provided (#1345) ...

fixes #1340 and allows for batching multiple audio files less than 30s each

2025-08-16 14:30:50 +03:00

..

assets

Use Silero VAD in Batched Mode (#936)

2024-10-24 12:05:25 +03:00

__init__.py

New PR for Faster Whisper: Batching Support, Speed Boosts, and Quality Enhancements (#856)

2024-07-18 16:48:52 +07:00

audio.py

Remove torch dependency, Faster numpy Feature extraction (#1106)

2024-11-14 12:57:10 +03:00

feature_extractor.py

Remove torch dependency, Faster numpy Feature extraction (#1106)

2024-11-14 12:57:10 +03:00

tokenizer.py

Filter out non_speech_tokens in suppressed tokens (#898)

2024-07-05 14:43:11 +07:00

transcribe.py

only merge when clip_timestamps are not provided (#1345)

2025-08-16 14:30:50 +03:00

utils.py

feat: Allow loading of private HF models (#1309)

2025-06-02 14:12:34 +03:00

vad.py

Remove Silence in Batched transcription (#1297)

2025-08-06 03:30:59 +03:00

version.py

bump version to 1.2.0

2025-08-06 03:31:36 +03:00