admin-valentin/WhisperLiveKit
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

new command to get simulstreaming backend

Browse source
This commit is contained in:
Quentin Fuxa 2025-07-03 10:24:02 +02:00
parent 5daaf77258
commit b362eccb23
3 changed files with 9 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -35,7 +35,7 @@ WhisperLiveKit consists of three main components:
- **Confidence Validation** – Immediately validate high-confidence tokens for faster inference (WhisperStreaming only) - **Confidence Validation** – Immediately validate high-confidence tokens for faster inference (WhisperStreaming only)
- **Buffering Preview** – Displays unvalidated transcription segments (not compatible with SimulStreaming yet) - **Buffering Preview** – Displays unvalidated transcription segments (not compatible with SimulStreaming yet)
- **Punctuation-Based Speaker Splitting [BETA]** - Align speaker changes with natural sentence boundaries for more readable transcripts - **Punctuation-Based Speaker Splitting [BETA]** - Align speaker changes with natural sentence boundaries for more readable transcripts
- **SimulStreaming Backend** - Ultra-low latency transcription using state-of-the-art AlignAtt policy. The code is not bundled directly in this repository. To retrieve it, please run `python whisperlivekit/download_simulstreaming_backend.py` - **SimulStreaming Backend** - Ultra-low latency transcription using state-of-the-art AlignAtt policy. The code is not bundled directly in this repository. To retrieve it, please run `whisperlivekit-download-simulstreaming`
## Quick Start ## Quick Start
@ -298,4 +298,4 @@ Capture discussions in real-time for meeting transcription, help hearing-impaire
We extend our gratitude to the original authors of: We extend our gratitude to the original authors of:
| [Whisper Streaming](https://github.com/ufal/whisper_streaming) | [SimulStreaming](https://github.com/ufal/SimulStreaming) | [Diart](https://github.com/juanmc2005/diart) | [OpenAI Whisper](https://github.com/openai/whisper) | | [Whisper Streaming](https://github.com/ufal/whisper_streaming) | [SimulStreaming](https://github.com/ufal/SimulStreaming) | [Diart](https://github.com/juanmc2005/diart) | [OpenAI Whisper](https://github.com/openai/whisper) |
| -------- | ------- | -------- | ------- | | -------- | ------- | -------- | ------- |

3
setup.py
View file

@ -40,6 +40,7 @@ setup(
entry_points={ entry_points={
'console_scripts': [ 'console_scripts': [
'whisperlivekit-server=whisperlivekit.basic_server:main', 'whisperlivekit-server=whisperlivekit.basic_server:main',
'whisperlivekit-download-simulstreaming=whisperlivekit.download_simulstreaming_backend:main',
], ],
}, },
classifiers=[ classifiers=[
@ -52,4 +53,4 @@ setup(
"Topic :: Multimedia :: Sound/Audio :: Speech", "Topic :: Multimedia :: Sound/Audio :: Speech",
], ],
python_requires=">=3.9", python_requires=">=3.9",
) )

7
whisperlivekit/download_simulstreaming_backend.py
View file

@ -24,7 +24,10 @@ def download_files_from_github(api_url, local_dir):
# Recursive call for subdirectories # Recursive call for subdirectories
download_files_from_github(item['url'], os.path.join(local_dir, item['name'])) download_files_from_github(item['url'], os.path.join(local_dir, item['name']))
if __name__ == "__main__": def main():
print(f"Downloading files into {TARGET_DIR} ...") print(f"Downloading files into {TARGET_DIR} ...")
download_files_from_github(GITHUB_API_URL, TARGET_DIR) download_files_from_github(GITHUB_API_URL, TARGET_DIR)
print("✅ Download completed successfully.") print("✅ Download completed successfully.")
if __name__ == "__main__":
main()