GitLab

Future work items:
- length computation of GriffinLim
- better way to make InverseMelScale work in inference_mode

- Move wav2vec2 pretrained weights to `torchaudio.pipelines` namespace to align with #1872.
- Split `Wav2Vec2PretrainedModelBundle` into `Wav2Vec2Bundle` (for pre-training model) and  `Wav2Vec2ASRBundle` (for models fine-tuned for ASR).
- Update base URL

To handle batched input properly.

Move the computation of `#classes -> #bits` to the constructor of WaveRNN and attach it to the instance, so that it can be reused elsewhere.

This commit merges wav2vec2/hubert factory functions for pre-training and fine-tuning. In #1829, we added parameters to customize the models that are not part of architecture, and `aux_num_out` falls into this category, so it is no longer necessary to have separate functions. This concludes the wav2vec2/HuBERT API update in release 0.10.

The summary of BC-breaking changes on wav2vec2 APIs between 0.9 and 0.10 (when this commit is incorporated)
1. `Wav2Vec2Model.extract_features`
In 0.9, it was returning the output from `FeatureExtractor` module. In 0.10, it returns the list of outputs from the intermediate layers of `TransformerEncoder` block.
2. `wav2vec2_base(num_out: int)` -> `wav2vec2_base(<dropout_params:float>, aux_num_out: Optional[int]=None)`
    - `num_out` was renamed to `aux_num_out` and optional. If it is omitted, the resulting model does not have the linear layer for fine-tuning.
    - Added dropout parameters.

This commit makes the following changes
1. Make the factory function with full customizability public.
    i.e. `_get_model(...) -> wav2vec2_model(...)`.
2. Change the other architecture-specific factory functions so that they accept parameters not related to the model architecture (such as dropout).
    i.e. `wav2vec2_base() -> wav2vec2_base(encoder_projection_dropout, encoder_attention_dropout, encoder_ff_interm_dropout, ...)`

### Why?

While adding the pre-trained weight support, I realized that separating API for model construction and pre-trained support achieves simple code organization because of the good separation of concern. As mentioned in #1821, in this framework,
  1. Model implementation is responsible for computation logic,
  2. factory functions are responsible for customizability and model construction,
  3. and pre-trained weight API is responsible for constructing a model and loading pre-trained weights along with the complementary information (such as pre-processing and class labels).

(note: for simple models, combining 1 and 2 is also okay.)

This means that factory functions has to support all the customizability required by pre-trained weight API. The current implementation uses the internal function like `from .model import Wav2Vec2Model, _get_model`, which is a bit strange.

This PR rectifies it by making the mother factory function public.
This also clarifies the purpose of having the other factory functions as public API, which is just a syntax sugar for constructing un-trained model with specific architecture. So this commit also adds supplemental parameters to them.

Add pretrained weights from https://github.com/pytorch/fairseq/tree/main/examples/wav2vec#pre-trained-models
- Wav2Vec 2.0 Base / Large / Large (LV-60)
- XLSR-53

This commit adds
- HUBERT_LARGE
- HUBERT_XLARGE
- HUBERT_ASR_XLARGE

* Deprecate data utils

- The design criteria of diskcache_iterator and bg_iterator are not well-specified
- The implementation does not improve the performance due to GIL and threading

1. Fix the HuBERT xlarge model config
2. In the 48 transformer layers of HuBERT xlarge model, very few elements deviate from the equivalent model of fairseq, and exceeds the default atol 1e-5. This commit relax it to 3e-5 for the specific test.

Writing scripted HuBERT XLarge models fail on Windows CI.