Dockerized REST API service for Persian/Farsi speech-to-text conversion. Utilizes
m3hrdadfi/wav2vec2-large-xlsr-persian model.
| .env.docker | ||
| .env.sample | ||
| .gitignore | ||
| Dockerfile | ||
| main.py | ||
| README.md | ||
| requirements.txt | ||
Persian Speech-to-text
Build docker image
docker build . -t rbehzadan/speech2text-fa:1.0.0
Run docker container
docker run --rm --name speech2text-da -p 8000:8000 -it rbehzadan/speech2text-fa:1.0.0
Testing
With curl
curl -X POST "http://localhost:8000/transcribe" -H "accept: application/json" -H "Content-Type: multipart/form-data" -F "audio_file=@sample.wav"
With HTTPie
http -f POST http://localhost:8000/transcribe audio_file@sample.wav