Emmanuel Schmidbauer
Emmanuel Schmidbauer
im running into similiar issue with latest stable release on 2x 4090s ``` python -m vllm.entrypoints.api_server --model TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ \ --dtype auto --tokenizer mistralai/Mixtral-8x7B-Instruct-v0.1 \ --quantization awq --trust-remote-code \ --tensor-parallel-size 2...
I was more curious about fine-tuning TTS. I dont see steps on how to train/tune TTS in the repo.
make sure you run `python -m unidic download`
I believe piper can run in the browser using [this](https://github.com/wide-video/piper-wasm) Looks like a patch is required in [piper](https://github.com/rhasspy/piper/compare/master...wide-video:piper:wide.video) I wonder if we can get that merged back to this repo...
@csukuangfj This is great, thanks so much !
@HHousen Any chance you could submit a PR to get that [change](https://github.com/m-bain/whisperX/compare/main...HHousen:whisperX:main) merged?
Would it be possible to implement this so realtime data can be sent from any source (e.g. websockets, reading large file, etc...)
Im experiencing same issue @KevinLee1993 described. Any information on a solution would be helpful. also thanks for sharing this project!
i think this is an issue with python>=3.11 if you install `mecab-python3==1.0.6` it seems to work
anyway you can limit this to english only? I tried this branch and it filled up my disk.