CosyVoice
CosyVoice copied to clipboard
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
使用tensorrt对flow进行加速后,sft可以使用,但zero-shot合成的音频是杂音 文本:今天天气真的很好呀 [zero_shot_500.wav.zip](https://github.com/user-attachments/files/17355003/zero_shot_500.wav.zip) tensorrt推理过程  
问题:通过webui.py运行,推理模式选择预训练音色,点击生成音频报错,服务端显示:RuntimeError: "addmm_impl_cpu_" not implemented for 'Half',具体报错信息如下: 2024-09-27 16:32:01,942 INFO get sft inference request tn 我是通义实验室语音团队全新推出的生成式语音大模型,提供舒适自然的语音合成能力。 to 我是通义实验室语音团队全新推出的生成式语音大模型,提供舒适自然的语音合成能力。 0%| | 0/1 [00:00
合成音频时,文本分段后,每段的音频开始均会有滴的一声,听起来很奇怪,如下图,在切分后的每段文本开始前,总会有个明显的滴的一声噪音  [zero_shot_9222.wav.zip](https://github.com/user-attachments/files/17344112/zero_shot_9222.wav.zip)
1、/project/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `**pip install peft**`. 这个使用pip install...
能不能和 gpt-sovits 一样根据多段对照文本生成声音, 然后生成缓存文件, 该文件可供下载 后续根据该声音特征文件, 重新合成声音
the flow model in cosyvoice, its encoder Conformers contains position embeds while in its decoder transformers, I see no such addition. is that means no benifit here in flow-matching? sorry...
**Describe the bug** from cosyvoice.cli.cosyvoice import CosyVoice from cosyvoice.utils.file_utils import load_wav import torchaudio cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # zero_shot usage, for Chinese/English/Japanese/Cantonese/Korean prompt_speech_16k = load_wav('./33.wav', 16000) for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物,那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐,笑容如花儿般绽放。',...
2024-09-12 09:30:52,827 - modelscope - INFO - PyTorch version 2.0.1 Found. 2024-09-12 09:30:52,828 - modelscope - INFO - Loading ast index from C:\Users\Administrator\.cache\modelscope\ast_indexer 2024-09-12 09:30:52,950 - modelscope - INFO -...
之前使用python 3.8环境 各种报错最后安装 tts 说是至少python 3.9 以上 然后重装了 python 的 3.11 环境 目前报这个错 (cosyvoicep11) G:\python\CosyVoicep11>python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M Traceback (most recent call last): File "G:\python\CosyVoicep11\webui.py", line 20, in...