Instructions to use HeddyRogue/PocketTTS-VolgaGerm-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use HeddyRogue/PocketTTS-VolgaGerm-ONNX with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("HeddyRogue/PocketTTS-VolgaGerm-ONNX") 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
PocketTTS-VolgaGerm
ONNX-exported models for use with PocketTTS.cpp.
Files
onnx-models/
| File | Description |
|---|---|
flow_lm_flow_int8.onnx |
Flow language model (int8 quantized) |
flow_lm_main_int8.onnx |
Main flow language model (int8 quantized) |
mimi_decoder_int8.onnx |
Mimi decoder (int8 quantized) |
mimi_encoder.onnx |
Mimi encoder |
text_conditioner.onnx |
Text conditioner |
Root
| File | Description |
|---|---|
tokenizer.model |
SentencePiece tokenizer model |
License
MIT
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support