llmkira/vitsserver

🌻 VITS ONNX TTS server designed for fast inference 🔥

vitsserver's Issues

generate_voice生成的语音每句前后包含[zh]

请问有没有地方关掉？

Update Readme

• 模型目录结构的tree图
• 一些附加说明和删改
• 关于批次推理的说明

这个整个部署到自己电脑上连同环境依赖这些总的文件大吗？

这个整个部署到自己电脑上连同环境依赖这些总的文件大吗？

ncnn

onnxruntime ScatterND_3243 error

when I run pth2onnx.py， change pth to onnx，it occurs error below：

/usr/local/lib64/python3.6/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:56: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'CPUExecutionProvider'
"Available providers: '{}'".format(name, ", ".join(available_provider_names)))
2023-07-17 14:04:22.586812890 [E:onnxruntime:, sequential_executor.cc:346 Execute] Non-zero status code returned while running ScatterND node. Name:'ScatterND_3243' Status Message: invalid indice found, indice = -1
Traceback (most recent call last):
File "pth2onnx.py", line 150, in
return_bytes=True
File "pth2onnx.py", line 139, in warp_pth
write_down=True)
File "pth2onnx.py", line 125, in convert_model
onnx_output = RunONNX(model=onnx_model, providers=providers).run(model_input=ort_inputs)
File "/data/user/liukai/test/tts/VitsServer-main/onnx_infer/utils/onnx_utils.py", line 42, in run
input_feed=model_input
File "/usr/local/lib64/python3.6/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 192, in run
return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Non-zero status code returned while running ScatterND node. Name:'ScatterND_3243' Status Message: invalid indice found, indice = -1

what's the problem？Who can help me？

ONNX converting issues

Hello, I faced these errors while converting to onnx

TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert (discriminant >= 0).all()
Warning: Constant folding - Only steps=1 can be constant folded for opset >= 10 onnx::Slice op. Constant folding not applied.
WARNING: The shape inference of prim::Constant type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function.

What may be wrong? Thanks

HuBERT-VITS & W2V2-VITS

此项任务暂时搁置到llmkira主套装开发完毕

非空检查，健壮性。考虑无输入

VitsServer/event.py

Line 362 in c114751

# _task_list.append(test)