automatic_model_training notebook no longer working #296
Description
Having some issues with:
https://github.com/dscripka/openWakeWord/blob/main/notebooks/automatic_model_training.ipynb
- Running the Google colab as is, you'll get a
ModuleNotFoundError: No module named 'piper'error. - After fixing the above, you'll get the following error:
TypeError: generate_samples() missing 1 required positional argument: 'model' - I wasn't 100% on how to fix the above, but passed this into the generate_samples function
model="piper-sample-generator/models/en_US-libritts_r-medium.pt"and then I still ran into the following errors:
Step 2 Augment the generated clips error:
/usr/local/lib/python3.12/dist-packages/torchaudio/_backend/utils.py:213: UserWarning: In 2.9, this function's implementation will be changed to use torchaudio.load_with_torchcodec` under the hood. Some parameters like ``normalize``, ``format``, ``buffer_size``, and ``backend`` will be ignored. We recommend that you port your code to rely directly on TorchCodec's decoder instead: https://docs.pytorch.org/torchcodec/stable/generated/torchcodec.decoders.AudioDecoder.html#torchcodec.decoders.AudioDecoder.
warnings.warn(
/usr/local/lib/python3.12/dist-packages/torchaudio/_backend/ffmpeg.py:88: UserWarning: torio.io._streaming_media_decoder.StreamingMediaDecoder has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
s = torchaudio.io.StreamReader(src, format, None, buffer_size)
Traceback (most recent call last):
File "/content/openwakeword/openwakeword/train.py", line 794, in <module>
compute_features_from_generator(positive_clips_train_generator, n_total=len(os.listdir(positive_train_output_dir)),
File "/content/openwakeword/openwakeword/utils.py", line 575, in compute_features_from_generator
audio_data = next(generator)
^^^^^^^^^^^^^^^
File "/content/openwakeword/openwakeword/data.py", line 680, in augment_clips
raise ValueError("Error! Clip does not have the correct sample rate!")
ValueError: Error! Clip does not have the correct sample rate!
Step 3 (Train model) error:
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
/usr/local/lib/python3.12/dist-packages/torch_audiomentations/utils/io.py:27: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. This deprecation is part of a large refactoring effort to transition TorchAudio into a maintenance phase. The decoding and encoding capabilities of PyTorch for both audio and video are being consolidated into TorchCodec. Please see https://github.com/pytorch/audio/issues/3902 for more information. It will be removed from the 2.9 release.
torchaudio.set_audio_backend("soundfile")
/usr/local/lib/python3.12/dist-packages/torchaudio/_internal/module_utils.py:71: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
return func(*args, **kwargs)
Traceback (most recent call last):
File "/content/openwakeword/openwakeword/train.py", line 823, in <module>
input_shape = np.load(os.path.join(feature_save_dir, "positive_features_test.npy")).shape[1:]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/dist-packages/numpy/lib/_npyio_impl.py", line 455, in load
fid = stack.enter_context(open(os.fspath(file), "rb"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: '/content/my_custom_model/hey_sebastian/positive_features_test.npy'