RuntimeError: Could not infer dtype of numpy.float32

[reddere]

Not even working. Using the offline model and config (the one with 98M params) with Web UI @Plachtaa

  File "E:\Users\rober\Coding\githubs\seed-vc-main\app_vc.py", line 230, in voice_conversion
    source_audio = torch.tensor(source_audio).unsqueeze(0).float().to(device)
RuntimeError: Could not infer dtype of numpy.float32

Here's the whole traceback from the command to error

command
python app_vc.py --checkpoint E:\Users\rober\Coding\githubs\seed-vc-main\checkpoints\DiT_seed_v2_uvit_whisper_small_wavenet_bigvgan_pruned.pth --config E:\Users\rober\Coding\githubs\seed-vc-main\configs\presets\config_dit_mel_seed_uvit_whisper_small_wavenet.yml --fp16 True

terminal

sets\x5cconfig_dit_mel_seed_uvit_whisper_small_wavenet.yml --fp16 True;84a08dbe-dfd3-4510-a889-4efa32db5805
A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.1.3 as it may crash. To support both 1.x and 2.x
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.

If you are a user of the module, the easiest solution will be to
downgrade to 'numpy<2' or try to upgrade the affected module.
We expect that some modules will need time to support NumPy 2.

Traceback (most recent call last):  File "E:\Users\rober\Coding\githubs\seed-vc-main\app_vc.py", line 4, in <module> 
    import torch
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\__init__.py", line 2120, in <module>
    from torch._higher_order_ops import cond
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\_higher_order_ops\__init__.py", line 1, in <module>
    from .cond import cond
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\_higher_order_ops\cond.py", line 5, in <module>
    import torch._subclasses.functional_tensor
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\_subclasses\functional_tensor.py", line 42, in <module>
    class FunctionalTensor(torch.Tensor):
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\_subclasses\functional_tensor.py", line 258, in FunctionalTensor
    cpu = _conversion_method_template(device=torch.device("cpu"))
E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\_subclasses\functional_tensor.py:258: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\utils\tensor_numpy.cpp:84.)
  cpu = _conversion_method_template(device=torch.device("cpu"))
Using device: cuda
Using fp16: True
E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\nn\utils\weight_norm.py:134: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
  WeightNorm.apply(module, name, dim)
E:\Users\rober\Coding\githubs\seed-vc-main\modules\commons.py:462: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  state = torch.load(path, map_location="cpu")
Warning: Skipped loading some keys due to shape mismatch: {'estimator.input_pos', 'estimator.f0_embedder.weight'}
cfm loaded
length_regulator loaded
campplus_cn_common.bin: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 28.0M/28.0M [00:00<00:00, 42.3MB/s]
E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\huggingface_hub\file_download.py:157: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in E:\Users\rober\Coding\githubs\seed-vc-main\checkpoints\models--funasr--campplus. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
  warnings.warn(message)
config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.41k/1.41k [00:00<?, ?B/s]
E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\huggingface_hub\file_download.py:157: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in E:\Users\rober\Coding\githubs\seed-vc-main\checkpoints\hf_cache\models--nvidia--bigvgan_v2_22khz_80band_256x. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
  warnings.warn(message)
E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\nn\utils\weight_norm.py:134: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
  WeightNorm.apply(module, name, dim)
Loading weights from nvidia/bigvgan_v2_22khz_80band_256x
bigvgan_generator.pt: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 449M/449M [00:10<00:00, 42.6MB/s]
E:\Users\rober\Coding\githubs\seed-vc-main\modules\bigvgan\bigvgan.py:481: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  checkpoint_dict = torch.load(model_file, map_location=map_location)
Removing weight norm...
The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.
0it [00:00, ?it/s]
config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.97k/1.97k [00:00<?, ?B/s]
E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\huggingface_hub\file_download.py:157: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in E:\Users\rober\Coding\githubs\seed-vc-main\checkpoints\hf_cache\models--openai--whisper-small. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
  warnings.warn(message)
model.safetensors: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 967M/967M [00:08<00:00, 114MB/s]
preprocessor_config.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 185k/185k [00:00<00:00, 5.60MB/s]
Running on local URL:  http://127.0.0.1:7861

To create a public link, set `share=True` in `launch()`.
E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\analytics.py:106: UserWarning: IMPORTANT: You are using gradio version 4.44.0, however version 4.44.1 is available, please upgrade. 
--------
  warnings.warn(
Traceback (most recent call last):
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\queueing.py", line 536, in process_events
    response = await route_utils.call_process_api(
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api
    output = await app.get_blocks().process_api(
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\blocks.py", line 1935, in process_api
    result = await self.call_function(
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\blocks.py", line 1532, in call_function
    prediction = await utils.async_iteration(iterator)
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\utils.py", line 671, in async_iteration
    return await iterator.__anext__()
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\utils.py", line 664, in __anext__
    return await anyio.to_thread.run_sync(
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\anyio\_backends\_asyncio.py", line 2461, in run_sync_in_worker_thread
    return await future
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\anyio\_backends\_asyncio.py", line 962, in run
    result = context.run(func, *args)
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\utils.py", line 647, in run_sync_iterator_async
    return next(iterator)
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\gradio\utils.py", line 809, in gen_wrapper
    response = next(iterator)
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\utils\_contextlib.py", line 36, in generator_context
    response = gen.send(None)
  File "E:\Users\rober\Coding\githubs\seed-vc-main\.venv\lib\site-packages\torch\utils\_contextlib.py", line 36, in generator_context
    response = gen.send(None)
  File "E:\Users\rober\Coding\githubs\seed-vc-main\app_vc.py", line 230, in voice_conversion
    source_audio = torch.tensor(source_audio).unsqueeze(0).float().to(device)
RuntimeError: Could not infer dtype of numpy.float32

[Plachtaa]

Sorry for the issue, please try downgrading numpy to 1.26.4, I will revisit the requirements and make a fix soon

[reddere]

thanks @Plachtaa , this worked. Would a newer version of numpy improve the quality of the output? It sounds really robotic in some specific parts (using numpy with 1.26.4)