Gewu_Wang

Results 6 issues of Gewu_Wang

请问label存储的是什么

https://github.com/wenet-e2e/wetts/blob/39ab88dc5ad178a041686cb4062ac328f3b0aae0/wetts/frontend/g2p_prosody.py#L65C16-L65C16

"-"在任何场景下都会被tn为"减"吗?我在以下两个场景中,"-"两边都不是数字,但还是被tn为"减" tn: 注意一下这个wide-awake的含义 -> 注意一下这个wide减awake的含义 整体-表现非常好 -> 整体减表现非常好

下载最新代码,下载最新模型:https://www.modelscope.cn/models/iic/CosyVoice2-0.5B/files,运行示例合成代码,合成结果是胡言乱语。

对导出onnx和tensorRT的代码做了修改: ![Image](https://github.com/user-attachments/assets/21e4511b-fb8d-46cb-9f87-9987b753ba6b) ![Image](https://github.com/user-attachments/assets/6f4e69f2-da65-431f-ba0c-591560e6d0cb) 测试代码 ```python import sys import torchaudio import torch import tensorrt as trt flow_decoder_estimator_model = "pretrained_models/CosyVoice2-0.5B-dynamic_batch/flow.decoder.estimator.fp16.mygpu.plan" with open(flow_decoder_estimator_model, 'rb') as f: estimator_engine = trt.Runtime(trt.Logger(trt.Logger.INFO)).deserialize_cuda_engine(f.read()) if estimator_engine is None:...

stale