WhisperLive
WhisperLive copied to clipboard
collabora
A nearly-live implementation of OpenAI's Whisper.
Hi, @makaveli10 ! Great job on creating this! I like how well written and organized the code is. One thing that does seem a little bit off, as a design...
When there is no audio, the client() keeps on re-transcribing past audio. `from whisper_live.client import TranscriptionClient client = TranscriptionClient( "localhost", 9090, lang="ja", translate=False, model="small", use_vad=False, ) result = client() print(result)`...
Use the "av" library instead, which "just makes sense" since ```faster-library``` already uses it anyways. This removes the ```pyaudio``` dependency as well as that of ```scipy``` and ```numpy```. It also...
When following the docs for Whisper-TensorRT to [build the engine](https://github.com/collabora/WhisperLive/blob/main/TensorRT_whisper.md#whisper-tensorrt-engine), I am running into the error below when running the command in docker to build the model. It is saying...
i run the docker `ghcr.io/collabora/whisperbot-base:latest` and run the server , but when i send the request by client , i faced client:. ``` [INFO]: * recording setting [INFO]: Waiting for...
Hello, This is a fantastic tool, it works from the python client console just fine - though there are some hallucinations as noted in another issue. My overall goal here,...
Hello! I am currently using Twilio as my method to make phone calls + streaming the voice data to my server. However, when I tried to convert Twilio's x-mulaw audio...
I've been working on getting a version of this deployed to AWS on GPU compute for a project I'm working on. If there's any interest, let me know and I...
I've tried to look through documentation of other issues but have yet to find a clear solution. using a very simple test `from whisper_live.client import TranscriptionClient client = TranscriptionClient( "localhost",...
