Wendong Gan
Wendong Gan
@CorentinJ @yaguangtang @tail95 @zbloss @HumanG33k I am finetuning the encoder model by Chhinese data of 3100 persons. I want to know how to judge whether the train of finetune is...
@bfs18 ，Hi! Can you upload a copy of the whole “wavenet model: ns_wn-eval.tar.gz”? I also want to reloading ns_wn for teacher continue training. Thanks for your help! Look forward to...
Look forward to this problem being solved. I have calculated the current DP, I use 4 *A100, batch size 16, training libritts-460, I need to spend (15epoch x 7h+5epoch x...
@dohe0342 I'm interested in your pre-training model. Can you share your pre-training model with me? Thank you! my email is : [email protected]
Looking forward to your release~！
> > cosyvoice_pb2 > > 解决了吗？我遇到了 Traceback (most recent call last): File "server.py", line 18, in import cosyvoice_pb2 ModuleNotFoundError: No module named 'cosyvoice_pb2' 我也遇到这个问题了， 有朋友解决了么？
Release finetuned checkpoints for controllable human-like speech generation. 请问下，这个预计什么时候回发布呢？ 期待发布出来
期待发布训练代码
> 运行命令： python cosyvoice/bin/export_onnx.py --model_dir pretrained_models/CosyVoice2-0.5B > > 报错内容： Traceback (most recent call last): File "/Projects/TTS_metric/CosyVoice/cosyvoice/bin/export_onnx.py", line 116, in main() File "/Projects/TTS_metric/CosyVoice/cosyvoice/bin/export_onnx.py", line 112, in main torch.testing.assert_allclose(output_pytorch, torch.from_numpy(output_onnx).to(device), rtol=1e-2, atol=1e-4)...