Commit Graph

  • 6e3aa301f5 add batch speech tokenizer master lyuxiang.lx 2026-01-29 10:25:11 +00:00
  • 4f3be75dad Update README.md speech_tts 2025-12-17 03:09:57 +00:00
  • 51d9ec4259 update lyuxiang.lx 2025-12-17 02:25:32 +00:00
  • 527211591a During handling of the above exception, another exception occurred: pr/winteryx/20250708175702 winteryx 2025-07-08 09:57:07 +00:00
  • ca7f2c632f remove unnecessary files lyuxiang.lx 2025-05-30 17:51:38 +08:00
  • 115894fca7 update lyuxiang.lx 2025-05-23 16:40:49 +08:00
  • ca31cd7bb1 update lyuxiang.lx 2025-05-23 16:37:01 +08:00
  • 5712625369 add vllm file root 2025-05-08 09:01:01 +00:00
  • a820b78312 add hift.new.pt lyuxiang.lx 2025-05-06 11:29:32 +08:00
  • 653dee3741 (cosyvoice) G:\CosyVoice>python webui.py --port 50000 --model_dir pretrained_models/CosyVoice2-0.5B failed to import ttsfrd, use WeTextProcessing instead Sliding Window Attention is enabled but not implemented for sdpa; unexpected results may be encountered. D:\Program Files\Miniconda3\envs\cosyvoice\Lib\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. deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message) Traceback (most recent call last): File "D:\Program Files\Miniconda3\envs\cosyvoice\Lib\site-packages\transformers\utils\hub.py", line 424, in cached_files hf_hub_download( File "D:\Program Files\Miniconda3\envs\cosyvoice\Lib\site-packages\huggingface_hub\utils\_validators.py", line 106, in _inner_fn validate_repo_id(arg_value) File "D:\Program Files\Miniconda3\envs\cosyvoice\Lib\site-packages\huggingface_hub\utils\_validators.py", line 160, in validate_repo_id raise HFValidationError( huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: ''. pr/huang1100/20250429172009 huang1100 2025-04-29 09:20:13 +00:00
  • 60b054e54a set use_flow_cache=True when export lyuxiang.lx 2025-04-07 22:28:52 +08:00
  • f3bcc1af05 add flow cache model lyuxiang.lx 2025-04-07 21:48:19 +08:00
  • 72cd0800f0 开始的还能看明白,后面就找不到北了。我是用 Windows 操作的,我没有走最前面的那一步(Clone the repo),直接用 Anconda 的 power shell prompt。一路走下来,也没进什么文件夹。下载完模型后,这一步就卡住了: cd pretrained_models/CosyVoice-ttsfrd/ ,因为找不到pretrained_models 这个目录。后面的就更找不到了。相信没有做过这种部署的和我一样。 pr/sxyuan/20250401183253 sxyuan 2025-04-01 10:32:56 +00:00
  • 9bd5b08fc0 update lyuxiang.lx 2025-01-10 14:31:27 +08:00
  • fa7edb69b3 update lyuxiang.lx 2025-01-10 14:29:39 +08:00
  • f69d8993ee Update README.md mushenL 2025-01-09 08:04:50 +00:00
  • 8cb32bda1d update lyuxiang.lx 2025-01-02 22:11:29 +08:00
  • ec62e9159a Merge branch 'master' of https://www.modelscope.cn/iic/CosyVoice2-0.5B lyuxiang.lx 2025-01-01 00:54:53 +08:00
  • 4875ebcb4b update lyuxiang.lx 2025-01-01 00:52:25 +08:00
  • 2244ead84f Update README.md Cherrytest 2024-12-17 11:21:14 +00:00
  • a37aafb98b update lyuxiang.lx 2024-12-17 16:08:09 +08:00
  • 3fe5dc65c1 update lyuxiang.lx 2024-12-16 17:32:11 +08:00
  • 292895fb57 update lyuxiang.lx 2024-12-16 17:27:22 +08:00
  • b904de7725 update lyuxiang.lx 2024-12-16 15:18:21 +08:00
  • 9eb82e7502 update lyuxiang.lx 2024-12-13 16:06:53 +08:00
  • 9d5c22a8e6 update lyuxiang.lx 2024-12-13 11:58:05 +08:00
  • f18733ebd0 update lyuxiang.lx 2024-12-13 11:28:44 +08:00
  • 7989775dd0 update lyuxiang.lx 2024-12-12 19:06:17 +08:00
  • f0fdade79d System init configuration.json speech_tts 2024-12-10 02:33:01 +00:00
  • 55557eef4d System update meta information speech_tts 2024-12-10 02:33:01 +00:00
  • 52621a8e53 System init .gitattributes speech_tts 2024-12-10 02:33:00 +00:00