Modelpublic

pronoobie/piper-voices-hindi

sourceHugging Facemitupdated 26d agoView on Hugging Face

0likes37downloads

Model Card

Source script

Converted using the script https://github.com/CrispStrobe/CrispASR/blob/main/models/convert-piper-to-gguf.py the original model is https://huggingface.co/rhasspy/piper-voices/tree/main/hi/hi_IN/rohan/medium

Pre requisites

You need to download and install ffmpeg and crispasr.

How to run the model

For Windows

Assuming the model is in models diectory and the binary is in bin directory

bin\crispasr.exe --server --backend piper -m "models\hi_IN-rohan-medium.gguf" --port 8089 -l hi -t 8 --no-spoken-disclaimer --accept-marking-responsibility

For linux

./crispasr --server --backend piper -m "models/hi_IN-rohan-medium.gguf" --port 8089 -l hi -t 8 --no-spoken-disclaimer --accept-marking-responsibility

How to test

Windows

  curl -s http://localhost:8089/v1/audio/speech ^
  -H "Content-Type: application/json" ^
  -d "{\"model\":\"piper\",\"input\":\"हेलो, आप आज कैसे हैं? आज आपने बहुत अच्छा काम किया, मुझे आप पर बहुत गर्व है।\",\"spoken_disclaimer\":false,\"stream\":true,\"response_format\":\"pcm\"}" ^
  | ffplay -f s16le -ar 22050 -nodisp -

For Linux

  curl -s http://localhost:8089/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d "{\"model\":\"piper\",\"input\":\"हेलो, आप आज कैसे हैं? आज आपने बहुत अच्छा काम किया, मुझे आप पर बहुत गर्व है।\",\"spoken_disclaimer\":false,\"stream\":true,\"response_format\":\"pcm\"}" \
  | ffplay -f s16le -ar 22050 -nodisp -