metadata
license: cc-by-4.0
language:
- en
library_name: pocket-tts-onnx
base_model:
- kyutai/pocket-tts
pipeline_tag: text-to-speech
tags:
- tts
- voice-cloning
- onnx
- onnxruntime
Voice Clone Pro ONNX
Files
pocket-tts-onnx/
├── onnx/
│ ├── flow_lm_main.onnx # 303 MB - Flow LM transformer (FP32)
│ ├── flow_lm_main_int8.onnx # 76 MB - Flow LM transformer (INT8)
│ ├── flow_lm_flow.onnx # 39 MB - Flow network (FP32)
│ ├── flow_lm_flow_int8.onnx # 10 MB - Flow network (INT8)
│ ├── mimi_decoder.onnx # 42 MB - Audio decoder (FP32)
│ ├── mimi_decoder_int8.onnx # 23 MB - Audio decoder (INT8)
│ ├── mimi_encoder.onnx # 73 MB - Voice encoder
│ └── text_conditioner.onnx # 16 MB - Text embeddings
├── reference_sample.wav # Example voice reference
├── tokenizer.model # SentencePiece tokenizer
├── pocket_tts_onnx.py # Inference wrapper
├── generate.py # CLI script
├── requirements.txt # Python dependencies
└── README.md