Instructions to use AXERA-TECH/CosyVoice2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/CosyVoice2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="AXERA-TECH/CosyVoice2")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/CosyVoice2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| LLM_DIR=CosyVoice-BlankEN-Ax650-prefill_512/ | |
| TOKEN2WAV_DIR=token2wav-axmodels/ | |
| openssl req -newkey rsa:2048 -new -nodes -x509 -days 365 -keyout server.key -out server.crt -subj "/C=CN/ST=Beijing/L=Beijing/O=YourOrg/CN=localhost" | |
| rm output*.wav | |
| ./main_api_ax650 \ | |
| --template_filename_axmodel "${LLM_DIR}/qwen2_p128_l%d_together.axmodel" \ | |
| --token2wav_axmodel_dir $TOKEN2WAV_DIR \ | |
| --n_timesteps 10 \ | |
| --axmodel_num 24 \ | |
| --bos 0 --eos 0 \ | |
| --filename_tokenizer_model "http://127.0.0.1:12345" \ | |
| --filename_post_axmodel "${LLM_DIR}/qwen2_post.axmodel" \ | |
| --filename_decoder_axmodel "${LLM_DIR}/llm_decoder.axmodel" \ | |
| --filename_tokens_embed "${LLM_DIR}/model.embed_tokens.weight.bfloat16.bin" \ | |
| --filename_llm_embed "${LLM_DIR}/llm.llm_embedding.float16.bin" \ | |
| --filename_speech_embed "${LLM_DIR}/llm.speech_embedding.float16.bin" \ | |
| --continue 0 \ | |
| --prompt_files prompt_files | |
| chmod 777 output*.wav | |