Dhwani - Voice Mode For Kannada

• Dhwani is a self-hosted platform designed to provide Voice mode interaction for Kannada and Indian languages.

• This platform leverages various tools and models to parse, transcribe, and improve conversation ultimately providing high-quality audio interactions

• An experiment to build a production grade inference pipeline

• Voice Demo

• TTS - Text to Speech

curl -X 'POST' \
  'https://gaganyatri-tts-indic-server-cpu.hf.space/v1/audio/speech' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{"input": "ಉದ್ಯಾನದಲ್ಲಿ ಮಕ್ಕಳ ಆಟವಾಡುತ್ತಿದ್ದಾರೆ ಮತ್ತು ಪಕ್ಷಿಗಳು ಚಿಲಿಪಿಲಿ ಮಾಡುತ್ತಿವೆ.", "voice": "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speakers voice sounding clear and very close up.",, "response_type": "wav"}'  -o audio_kannada_gpu_cloud.wav

• ASR - Automatic Speech Recognition

curl -X 'POST' \
  'https://gaganyatri-asr-indic-server-cpu.hf.space/transcribe/?language=kannada' \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -F 'file=@audio_kannada_gpu_cloud.wav;type=audio/x-wav'

• Translate - Kannada to Hindi

curl -X 'POST'
'https://gaganyatri-translate-indic-server-cpu.hf.space/translate?src_lang=kan_Knda&tgt_lang=eng_Latn&device_type=cpu'
-H 'accept: application/json'
-H 'Content-Type: application/json'
-d '{ "sentences": [ "ನಮಸ್ಕಾರ, ಹೇಗಿದ್ದೀರಾ?", "ಶುಭೋದಯ!" ], "src_lang": "kan_Knda", "tgt_lang": "eng_Latn" }'