Update faster-whisper based on SYSTRAN fork #7
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* add distil-large-v3 * Update README.md * use fp16 weights from Systran
* Bugfix: code breaks if audio is empty Regression since #732 PR
* Foolproof: Disable VAD if clip_timestamps is in use Prevent silly things to happen.
* CUDA version note and updated instructions in README * ctranslate2 downgrade note, cuDNN v9 consideration * clearer note on cuDNN v9 package
* add hotword params --------- Co-authored-by: jax <[email protected]>
* Clarify documentation for hotwords * Remove redundant type specifications
Spelling correction for copy/pasters
…847) * chore: add distil models to WhisperModel init docstring and download_model docstring
Docker file improvements Co-authored-by: Fedir Zadniprovskyi <[email protected]>
Co-authored-by: Fedir Zadniprovskyi <[email protected]>
* Fix window_size_samples to 512 * Update SileroVADModel * Replace ONNX file with V5 version
* Filter out non_speech_tokens in suppressed tokens
…y Enhancements (#856) Batching Support, Speed Boosts, and Quality Enhancements --------- Co-authored-by: Hargun Mujral <[email protected]> Co-authored-by: MahmoudAshraf97 <[email protected]>
…eline` and fix word timestamps for batched inference (#921) * fix word timestamps for batched inference * remove hf pipeline
* revert back to using PyAV instead of torch audio * Update audio.py
Replace Pyannote VAD with Silero to reduce code duplication and requirements
* pad to 3000 instead of `feature_extractor.nb_max_frames` * correct trimming for batched features
Co-authored-by: Mahmoud Ashraf <[email protected]>
* Update README.md * Update README.md * Update version.py * Update README.md * Update README.md * Update README.md
… initial timestamp is not zero (#1141) Co-authored-by: Mahmoud Ashraf <[email protected]>
* Supported new options for batched transcriptions: * `language_detection_threshold` * `language_detection_segments` * Updated `WhisperModel.detect_language` function to include the improved language detection from #732 and added docstrings, it's now used inside `transcribe` function. * Removed the following functions as they are no longer needed: * `WhisperModel.detect_language_multi_segment` and its test * `BatchedInferencePipeline.get_language_and_tokenizer` * Added tests for empty audios
* Added test for `multilingual` option with english-german audio * removed `output_language` argument as it is redundant, you can get the same functionality with `task="translate"` * use the correct `encoder_output` for language detection in sequential transcription * enabled `multilingual` functionality for batched inference
* update version * Update CPU benchmarks * Updated GPU benchmarks * .. * more gpu benchmarks
* Add Open-dubbing into community projects * Update URL
Co-authored-by: Mahmoud Ashraf <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.