Spaces:
Sleeping
Sleeping
Commit History
-
Merge branch 'main' of https://huggingface.co/spaces/aadnk/whisper-webui
8063dc1
-
Allow specifying model large-v1 (#33)
- Allow specifying large-v1 (af6fd0e034c92864d00758129a706ad1174816ce) - Add back large alias (2c1ede5aa9f9e4937085697a65a9aed9e26277fb)e01924c
-
Adding latest model (large-3)
4855017
-
Make a separate process timeout for diarization
3cd7d59 -
Make a separate process timeout for diarization
60d420f -
Merge branch 'main' of https://huggingface.co/spaces/aadnk/whisper-webui
a1b1422 -
Adding support for diarization
a1da02d
-
Clarify the need for CTranslate2 format. #8
6db3778
-
Merge branch 'main' of https://huggingface.co/spaces/aadnk/whisper-webui into main
a8eb534
-
Adding support for word timestamps
f55c594
-
Increase default maximum audio duration to 30 minutes
d7992fc -
Merge branch 'main' of https://huggingface.co/spaces/aadnk/whisper-webui into main
2d8fe1e -
Add inital prompt mode. GITLAB #7
Add a new configuration option `vad_initial_prompt_mode` in config.json5 and the application arguments that have the following two modes: * prepend_all_segments: Preprend the initial prompt to each VAD segment * prepend_first_segment: Only preprend the initial prompt the first VAD segment. This is useful if you're using the prompt to improve the accuracy of the transcription of unusual technical terms consistently throughout a lecture. You can add these terms to the prompt, and then set `vad_initial_prompt_mode` to `prepend_all_segments` to include the prompt in every VAD segment. Note that this will have no effect if you're not using a VAD.8031785
-
Switch to auto compute type
e694402 -
Switch to auto compute type
43f7897 -
Switch default implementation to faster-whisper
6565102 -
Add comments
198df44 -
Support CLI into faster-whisper
33ee1bb
-
Adding support for faster_whisper
This is a re-implementation of Whisper in CTranslate2 that can be 4x faster and use much less memory than OpenAI's Whisper.295de00
-
Add concurrency count to app.py. Set this to 1 by default.
This is to ensure that the WebUI is accessible from within proxies.d20404a
-
Add more configuration options to config.json5
1acaa19
-
Add more comments
8670926 -
Add configuration file and support for custom models
Custom models can be added to the configuration file, under the "models" section. See the comments for more details.44d964a