WhisperLive
WhisperLive copied to clipboard
collabora
A nearly-live implementation of OpenAI's Whisper.
我在尝试windows系统下操作。 服务器运行命令： `python run_server.py --port 9090 --backend faster_whisper` 客户端代码： ```python from whisper_live.client import TranscriptionClient client = TranscriptionClient( "localhost", 9090, lang="en", translate=False, model="small", use_vad=False, ) ``` 客户端输出日志： ```python PS D:\PY> &...
While using the medium model on a GPU system, I get this error message: `ERROR:root:[ERROR]: Sending data to client: sent 1000 (OK); then received 1000 (OK)` This mean the client...
I am using whisper-live==0.2.1 , faster-whisper==0.10.0 and Ctranslate2==4.0.0 Transcribing a 30-second audio file currently requires the same amount of time whether processed on a CPU or GPU, approximately 2 minutes....
`docker pull ghcr.io/collabora/whisperbot-base:latest` is very slow, taking about 20 min to pull with a data center network connection. Is there any way to speed this up?
Running the medium English model with VAD enabled, I've noticed a tendency to hallucinate phrases like "Thanks for watching!", "Thanks!", "That's all," etc.. I assume it's receiving some audio data...
I set up a local HLS stream playing a long video of someone talking. Everything seems great until after exactly 2 minutes in the transcription stops completely. INFO:faster_whisper:Processing audio with...
- optimize tensorrt docker build with multi stages - docker compose setup to build and run container with any model size from command line which builds the models on runtime...
on the version 0.4.1, CPU transcription consume less cpu than GPU +CPU. with: docker run -it -p 9090:9090 ghcr.io/collabora/whisperlive-cpu:latest  With GPU: docker run -it --gpus all -p 9090:9090 ghcr.io/collabora/whisperlive-gpu:latest...
When recording in real time, for example, I specified the output voice to be English, and the audio played was a mixture of Japanese and English, sometimes translating Japanese into...
This is an incomplete PR intended to start on addressing issues semi-related to #184. The `multilingual_input` option controls whether multiple languages should be expected in the input stream. If False...
