|
Download README.md from ICTNLP/indextts2_decoder: direct link, hf CLI and curl.
- Browser
- Download file 2.13 kB
-
https://huggingface.co/ICTNLP/indextts2_decoder/resolve/main/README.md
- Command line
-
hf download hf://ICTNLP/indextts2_decoder/README.md
-
curl -L -o README.md https://huggingface.co/ICTNLP/indextts2_decoder/resolve/main/README.md
2.13 kB
| language: | |
| - en | |
| - zh | |
| license: other | |
| license_name: bilibili-model-use-license-agreement | |
| license_link: https://github.com/ictnlp/FreezeEmpath/blob/main/licenses/IndexTTS2.txt | |
| tags: | |
| - speech | |
| - audio-to-audio | |
| - freezeempath | |
| # IndexTTS2-derived waveform decoder for FreezeEmpath | |
| This package converts FreezeEmpath speech tokens into 22,050 Hz mono waveforms, using components from [IndexTTS2](https://github.com/index-tts/index-tts), Amphion/MaskGCT, and NVIDIA BigVGAN. | |
| [FreezeEmpath model](https://huggingface.co/ICTNLP/FreezeEmpath) 路 [Code and instructions](https://github.com/ictnlp/FreezeEmpath) 路 [Paper](https://arxiv.org/abs/2604.18159) | |
| ## Contents and use | |
| - `config.yaml`: semantic codec and flow-matching configuration. | |
| - `semantic_codec.safetensors`: semantic codec weights. | |
| - `s2mel.pth`: flow-matching model weights. | |
| - `bigvgan_generator.pt`: vocoder weights. | |
| - `style.pt`, `prompt_condition.pt`, `ref_mel.pt`: fixed voice conditions used by the released example. | |
| Use the FreezeEmpath GitHub code and its bundled BigVGAN architecture configuration: | |
| ```bash | |
| python inference/codes2wav.py \ | |
| --cfg_path checkpoints/indextts2_codes2wav/config.yaml \ | |
| --model_dir checkpoints/indextts2_codes2wav \ | |
| --input_file outputs/answers.jsonl \ | |
| --output_dir outputs/wav --seed 42 | |
| ``` | |
| The input must contain `prediction_units` speech tokens generated by `inference/infer.py --s2s`; this package is not a standalone text-to-speech interface. The example uses a fixed voice, not user-selected speaker prompts. | |
| ## License | |
| This IndexTTS2-derived package is subject to the [bilibili Model Use License Agreement](https://github.com/ictnlp/FreezeEmpath/blob/main/licenses/IndexTTS2.txt). Individual BigVGAN and Amphion components retain their upstream MIT notices. See [third-party notices](https://github.com/ictnlp/FreezeEmpath/blob/main/THIRD_PARTY_NOTICES.md). | |
| Any modifications made to the original model in this Derivative Work are not endorsed, warranted, or guaranteed by the original right-holder of the original model, and the original right-holder disclaims all liability related to this Derivative Work. | |