Any-to-Any
Transformers
ONNX
Safetensors
multilingual
qwen2
omni
custom_code
audio
speech
voice cloning
live Streaming
realtime speech conversation
asr
tts
text-generation-inference
Instructions to use jdh-algo/JoyTTS-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jdh-algo/JoyTTS-v1 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("jdh-algo/JoyTTS-v1", trust_remote_code=True) model = AutoModel.from_pretrained("jdh-algo/JoyTTS-v1", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- e9d45a1418fc4abfce56797435fa96bd204c6bdf8d75510a70ff026c1383d72e
- Size of remote file:
- 186 MB
- SHA256:
- dab6eeb31aeaf88b443a0fb44ee75b74a0937c32f4bf64ee3a2830dfc5fbf507
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.