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

* check cuda installation

* check in build.sh

* use USE_CUDA

* Update pkg_helpers.bash

* Fix typo

To handle batched input properly.

* set cu113 for unittest_windows_gpu

* fix old logic

* Update .circleci/regenerate.py
Co-authored-by: Nikita Shulga <nikita.shulga@gmail.com>

* Limit Windows GPU testing to CUDA-11.3 only

Which is the only CUDA version that planned to be supported on Windows
for the upcoming release

* Move unittests to 11.3 as well

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

Adds an implementation of Emformer, a memory-efficient transformer architecture 
introduced in https://ieeexplore.ieee.org/document/9414560 that targets low-latency 
streaming speech recognition applications.

This commit adds
- HUBERT_LARGE
- HUBERT_XLARGE
- HUBERT_ASR_XLARGE