Instructions to use mehdi-hf/pocket-tts-farsi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use mehdi-hf/pocket-tts-farsi with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("mehdi-hf/pocket-tts-farsi") voice_state = tts_model.get_state_for_audio_prompt( "hf://kyutai/tts-voices/alba-mackenna/casual.wav" ) audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.") # Audio is a 1D torch tensor containing PCM data. scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy()) - Notebooks
- Google Colab
- Kaggle
Demo for this model on Spaces
Hi @mehdi-hf π€
I'm Linoy from the open-source team at Hugging Face - congrats on Pocket TTS Farsi!
We built with an agent an interactive demo app for it on Hugging Face Spaces, running on free ZeroGPU infrastructure: https://huggingface.co/spaces/hugging-apps/pocket-tts-farsi-demo
We would love to transfer this demo over to you or your organization - just let me know here which username or org to transfer to. We hope it can give your work more visibility, discoverability and let folks try it out.
In the future, feel free to already ship models with demos included. You can use this one as a blueprint to build by yourself or with the help of an agent - you can load the huggingface-spaces skill on Claude Code, Codex, Pi, etc.
Cheers,
Linoy
Hi Linoy,
That's great. Thank you. I originally created a space, but apparently it was a paid feature on HF, so i didn't add that. Having a space to demo is very good. Thank you again.
My username is: mehdi-hf
You can transfer it to me. :)
Best,
Mehdi