docs(notebook)-issue: Some possible issues in colab notebook of #84.

[chitsanfei]

Describe the bug

Some possible issues in Colab Notebook of #84. Step Training Cluster model and Use trained model

To Reproduce

Issue of Training Cluster model

Directly run Step Training Cluster model:

!svc train-cluster --output-path drive/MyDrive/so-vits-svc-fork/logs/44k

It occurred RuntimeError: File drive/MyDrive/so-vits-svc-fork/logs/44k cannot be opened., which means the output cluster file does not specify a default file name.

May need to be modified to
!svc train-cluster --output-path drive/MyDrive/so-vits-svc-fork/logs/44k/kmeans.pt

Issue of Use trained model (Use trained model (with cluster))

Run

!svc infer-cluster {NAME}.wav -r 0.1 -m drive/MyDrive/so-vits-svc-fork/logs/44k/ -c drive/MyDrive/so-vits-svc-fork/logs/44k/config.json -k drive/MyDrive/so-vits-svc-fork/logs/44k/kmeans.pt
display(Audio(f"{NAME}.out.wav", autoplay=True))

Return

Error: No such command 'infer-cluster'.

This code may need to be changed to:

!svc infer -cluster {NAME}.wav -s speaker -r 0.1 -m drive/MyDrive/so-vits-svc-fork/logs/44k/ -c drive/MyDrive/so-vits-svc-fork/logs/44k/config.json -k drive/MyDrive/so-vits-svc-fork/logs/44k/kmeans.pt
display(Audio(f"{NAME}.out.wav", autoplay=True))

Parameter -cluster needs to be separated from the previous command and it may need to specify -s parameter otherwise
it may occurred ValueError: Speaker None not in ['speaker']

Additional context

Log

Minibatch step 51/478: mean batch inertia: 65.0876693725586, ewa inertia: 65.07667463195396
Minibatch step 52/478: mean batch inertia: 64.66484069824219, ewa inertia: 64.9390382259093
Minibatch step 53/478: mean batch inertia: 65.48490142822266, ewa inertia: 65.12146770344484
Minibatch step 54/478: mean batch inertia: 64.38145446777344, ewa inertia: 64.87415257507425
Converged (lack of improvement in inertia) at step 54/478
Training clusters: 100% 1/1 [00:29<00:00, 29.71s/it]
Traceback (most recent call last):
  File "/usr/local/bin/svc", line 8, in <module>
    sys.exit(cli())
  File "/usr/local/lib/python3.9/dist-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/usr/local/lib/python3.9/dist-packages/click/core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "/usr/local/lib/python3.9/dist-packages/click/core.py", line 1657, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/usr/local/lib/python3.9/dist-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/usr/local/lib/python3.9/dist-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/usr/local/lib/python3.9/dist-packages/so_vits_svc_fork/__main__.py", line 623, in train_cluster
    main(
  File "/usr/local/lib/python3.9/dist-packages/so_vits_svc_fork/cluster/train_cluster.py", line 86, in main
    torch.save(checkpoint, output_path)
  File "/usr/local/lib/python3.9/dist-packages/torch/serialization.py", line 422, in save
    with _open_zipfile_writer(f) as opened_zipfile:
  File "/usr/local/lib/python3.9/dist-packages/torch/serialization.py", line 309, in _open_zipfile_writer
    return container(name_or_buffer)
  File "/usr/local/lib/python3.9/dist-packages/torch/serialization.py", line 287, in __init__
    super(_open_zipfile_writer_file, self).__init__(torch._C.PyTorchFileWriter(str(name)))
RuntimeError: File drive/MyDrive/so-vits-svc-fork/logs/44k cannot be opened.

[02:42:08] Version: 1.3.0
Usage: svc [OPTIONS] COMMAND [ARGS]...
Try 'svc -h' for help.

Error: No such command 'infer-cluster'.
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
[<ipython-input-18-347b9ce145ed>](https://localhost:8080/#) in <module>
      1 ##@title Use trained model (with cluster)
      2 get_ipython().system('svc infer-cluster {NAME}.wav -r 0.1 -m drive/MyDrive/so-vits-svc-fork/logs/44k/ -c drive/MyDrive/so-vits-svc-fork/logs/44k/config.json -k drive/MyDrive/so-vits-svc-fork/logs/44k/kmeans.pt')
----> 3 display(Audio(f"{NAME}.out.wav", autoplay=True))

[/usr/local/lib/python3.9/dist-packages/IPython/lib/display.py](https://localhost:8080/#) in __init__(self, data, filename, url, embed, rate, autoplay, normalize, element_id)
    112     def __init__(self, data=None, filename=None, url=None, embed=None, rate=None, autoplay=False, normalize=True, *,
    113                  element_id=None):
--> 114         if filename is None and url is None and data is None:
    115             raise ValueError("No audio data found. Expecting filename, url, or data.")
    116         if embed is False and url is None:

ValueError: rate must be specified when data is a numpy array or list of audio samples.

Running Environment

Fri Mar 24 02:06:17 2023       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.85.12    Driver Version: 525.85.12    CUDA Version: 12.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |
| N/A   37C    P8    10W /  70W |      0MiB / 15360MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

[34j]

I think -cluster is unnecessary and this is how it should be. Could you please also experiment with this to see if this works?

!svc infer {NAME}.wav -s speaker -r 0.1 -m drive/MyDrive/so-vits-svc-fork/logs/44k/ -c drive/MyDrive/so-vits-svc-fork/logs/44k/config.json -k drive/MyDrive/so-vits-svc-fork/logs/44k/kmeans.pt

I was fooled by copilot lol.

[chitsanfei]

I think -cluster is unnecessary and this is how it should be. Could you please also experiment with this to see if this works?

!svc infer {NAME}.wav -s speaker -r 0.1 -m drive/MyDrive/so-vits-svc-fork/logs/44k/ -c drive/MyDrive/so-vits-svc-fork/logs/44k/config.json -k drive/MyDrive/so-vits-svc-fork/logs/44k/kmeans.pt

I was fooled by copilot lol.

It works. Looking forward to your fix. 😚