Wall.E
**Is your feature request related to a problem? Please describe.** 希望加速模型推理，能够输出置信度和对齐的时间信息。 **Describe the solution you'd like** batch推理。 **Describe alternatives you've considered** 数据太多了的情况下，调用https://github.com/wenet-e2e/wenet/pull/2083这个推理接口，发现处理时间太长。 **Additional context**
运行实例https://modelscope.cn/models/iic/speech_diarization_eend-ola-en-us-callhome-8k/summary 报错信息： KeyError: 'speaker-diarization-inference is not in the pipelines registry group speaker-diarization. Please make sure the correct version of ModelScope library is used.' 版本信息：modelscope:'1.12.0' funasr: '1.0.19' Model related: @wenmengzhou @tastelikefeet...
**General Question** 需求： 调用说话人识别模型进行大规模数据推理； 使用模型： task='speaker-diarization', model='damo/speech_campplus_speaker-diarization_common', model_revision='v1.0.0' 示例用法： result = sd_pipeline(input_wav) 请问sd_pipeline()能进行batch推理吗？ Please @ corresponding people according to your problem: Pipeline related: @Firmament-cyou @wenmengzhou
Why should add_prenet be set to false? If it is not set to True, false is indeed better after the experiment, but I do not understand why, can you help...
Regarding model training and inference, I have a few questions that I would like to ask. 1. The model has started training. How much will the loss finally converge to?...
Can you provide alignment information for libritts data?
When the model converges to a relatively good situation, how much loss will be trained? In the current training code, the generator loss and the discriminator loss are？ The generation...
lang currently only supports en or zh? how to test code-switch text? Thanks. @FireRedTeam
**Describe the bug** A clear and concise description of what the bug is. 使用deepspeed训练examples/aishell/whisper，会报错： python3.10/site-packages/deepspeed/runtime/torch_autocast.py", line 97, in validate_nested_autocast raise AssertionError( AssertionError: torch.autocast is enabled outside DeepSpeed, but not in...