Repository Issue Activity (beta)

#339 [Bug]: Unable to pull Docker image or start Docker service

#212 CASIA 数据集 SER 性能不能复现，测试结果只有34，而不是report的70

#307 v0.1.2 Illegal instruction

#7 torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 214.66 GiB.

#215 时间戳数量和字符数量不匹配【词粒度模式返回时间戳】

#334 Clarification: does MODEL_LICENSE §3 "reference and learning purposes only" restrict commercial use? / 关于 §3 与商用边界的确认

#291 使用VAD + CAM++ speaker model + punctuation model 返回结果是空的

#343 在edge device 中，只能使用cpu推理吗

#311 Security: unsafe YAML config loading enables arbitrary code execution

#289 Loading SenseVoice with FunASR crashe

#290 trust_remote_code设置成True后报错。

#163 Is the SenseVoice-Large model currently commercialized?

#288 SenseVoice 和 Fun-ASR-Nano 的定位到底什么不同

#278 The problem of inaccurate speech recognition

#268 微调样本数据过长识别不出来

#265 语音评测的场景需求

#264 为什么我微调时，每个epoch内都有大量The grad norm is nan. Skipping updating the model.

#270 onnx推理时，除了中文，其他语言输出都没有标点符号

#274 IndexError: index 3 is out of bounds for dimension 1 with size 1

#256 TypeError: 'NoneType' object is not callable

#286 commercial use clarification for sensevoicesmall in paid desktop software

#287 I would like to confirm of License

#271 为什么在使用CPU的情况下耗时很长

#273 音频标注中是否支持噪声标注<|speech_noise|>

#280 decoding speed