audio/transcriptions may specify language

edgenai / edgen

⚡ Edgen: Local, private GenAI server alternative to OpenAI. No GPU required. Run AI models locally: LLMs (Llama2, Mistral, Mixtral...), Speech-to-text (whisper) and many others.

https://docs.edgen.co/

Apache License 2.0

323 stars 14 forks source link

audio/transcriptions may specify language #118

Open openmynet opened 5 months ago

openmynet commented 5 months ago

I see that both edgen_rt_whisper_cpp::TranscriptionArgs and whisper_cpp::WhisperParams offer a language field, which I hope means that specifying the desired language should work when using /v1/audio/transcriptions.

pedro-devv commented 5 months ago

The endpoint arguments aren't properly passed to whisper_cpp at the moment, but something that will definitely get addressed.