Gujarati Pocket TTS

This is a community finetune of Kyutai Pocket TTS, specifically focused on the Gujarati language.

It is a 6-layer student distilled from a 24-layer teacher. The tokenizer is SentencePiece. It speaks Gujarati and clones a voice from a short wav. Audio is 24 kHz. The weights are about 438 MB, and CPU is the intended way to run them. Guidance is already baked in, so generate with 1 step and temperature 0.3.

The paper is Pocket TTS. The base model is kyutai/pocket-tts, and the code is kyutai-labs/pocket-tts. The safetensors bundle includes Kyutai's codec weights, used here under CC-BY-4.0.

Samples

These are generations from this model.

Gujarati

જીવન હંમેશા આપણે ધારીએ તે રીતે ચાલતું નથી, પરંતુ ક્યારેક અણધારી ક્ષણો જ સૌથી સુંદર યાદો બની જાય છે.

Use

Install the library, or call it with uvx.

pip install pocket-tts

weights_path and tokenizer_path in the config are relative. Download this repo and run from that folder:

import scipy.io.wavfile
from pocket_tts import TTSModel

model = TTSModel.load_model(config="config.yaml")
voice = model.get_state_for_audio_prompt("my_voice.wav")
audio = model.generate_audio(voice, "નમસ્તે, તમે કેમ છો?")
scipy.io.wavfile.write("out.wav", model.sample_rate, audio.detach().cpu().numpy().squeeze())

The same config on the Hub:

model = TTSModel.load_model(config="hf://meeeetxd/pocket-tts-gujarati/config.yaml")

That address loads the yaml. The weight and tokenizer paths inside it stay relative, so model.safetensors and tokenizer.model still have to sit in the working directory. config.yaml and student.yaml are the same file.

uvx pocket-tts generate \
  --config config.yaml \
  --voice my_voice.wav \
  --text "નમસ્તે, તમે કેમ છો?" \
  --output-path out.wav

Model


Architecture	Pocket TTS flow LM, 6 layers, distilled from 24
Text	SentencePiece tokenizer, Gujarati language focus
Sample rate	24 kHz
Decode	1 step, temperature 0.3
Size	About 438 MB
Device	CPU

Happy to collaborate. If you like this model, give it a like, and follow me for future updates: https://www.linkedin.com/in/meet-patel21