Commit f8d8ffb5 authored by moto's avatar moto Committed by Facebook GitHub Bot
Browse files

Update prototype Conformer doc & docstring (#3191)

Summary:
To suppress local warning of flake8 <120

Pull Request resolved: https://github.com/pytorch/audio/pull/3191

Reviewed By: nateanl

Differential Revision: D44263027

Pulled By: mthrok

fbshipit-source-id: b3e48dba21fc5c9813f07e624a93f38a68956c6e
parent 3bd769f8
torchaudio.prototype.pipelines torchaudio.prototype.pipelines
============================== ==============================
...@@ -9,22 +10,16 @@ The pipelines subpackage contains APIs to models with pretrained weights and rel ...@@ -9,22 +10,16 @@ The pipelines subpackage contains APIs to models with pretrained weights and rel
RNN-T Streaming/Non-Streaming ASR RNN-T Streaming/Non-Streaming ASR
--------------------------------- ---------------------------------
EMFORMER_RNNT_BASE_MUSTC Pretrained Models
~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~
.. container:: py attribute
.. autodata:: EMFORMER_RNNT_BASE_MUSTC
:no-value:
EMFORMER_RNNT_BASE_TEDLIUM3
~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. container:: py attribute
.. autodata:: EMFORMER_RNNT_BASE_TEDLIUM3 .. autosummary::
:no-value: :toctree: generated
:nosignatures:
:template: autosummary/bundle_data.rst
EMFORMER_RNNT_BASE_MUSTC
EMFORMER_RNNT_BASE_TEDLIUM3
HiFiGAN Vocoder HiFiGAN Vocoder
--------------- ---------------
......
...@@ -18,12 +18,17 @@ EMFORMER_RNNT_BASE_MUSTC = RNNTBundle( ...@@ -18,12 +18,17 @@ EMFORMER_RNNT_BASE_MUSTC = RNNTBundle(
_segment_length=16, _segment_length=16,
_right_context_length=4, _right_context_length=4,
) )
EMFORMER_RNNT_BASE_MUSTC.__doc__ = """Pre-trained Emformer-RNNT-based ASR pipeline capable of performing both streaming and non-streaming inference. EMFORMER_RNNT_BASE_MUSTC.__doc__ = """Pre-trained Emformer-RNNT-based ASR pipeline capable of performing both
The underlying model is constructed by :py:func:`torchaudio.models.emformer_rnnt_base` and utilizes weights streaming and non-streaming inference.
trained on *MuST-C release v2.0* :cite:`CATTONI2021101155` dataset using training script ``train.py``
`here <https://github.com/pytorch/audio/tree/main/examples/asr/emformer_rnnt>`__ with ``num_symbols=501``. The underlying model is constructed by :py:func:`torchaudio.models.emformer_rnnt_base`
Please refer to :py:class:`torchaudio.pipelines.RNNTBundle` for usage instructions. and utilizes weights trained on *MuST-C release v2.0* :cite:`CATTONI2021101155` dataset
""" using training script ``train.py``
`here <https://github.com/pytorch/audio/tree/main/examples/asr/emformer_rnnt>`__
with ``num_symbols=501``.
Please refer to :py:class:`torchaudio.pipelines.RNNTBundle` for usage instructions.
"""
EMFORMER_RNNT_BASE_TEDLIUM3 = RNNTBundle( EMFORMER_RNNT_BASE_TEDLIUM3 = RNNTBundle(
...@@ -40,11 +45,14 @@ EMFORMER_RNNT_BASE_TEDLIUM3 = RNNTBundle( ...@@ -40,11 +45,14 @@ EMFORMER_RNNT_BASE_TEDLIUM3 = RNNTBundle(
_segment_length=16, _segment_length=16,
_right_context_length=4, _right_context_length=4,
) )
EMFORMER_RNNT_BASE_TEDLIUM3.__doc__ = """Pre-trained Emformer-RNNT-based ASR pipeline capable of performing both streaming and non-streaming inference. EMFORMER_RNNT_BASE_TEDLIUM3.__doc__ = """Pre-trained Emformer-RNNT-based ASR pipeline capable of performing both
streaming and non-streaming inference.
The underlying model is constructed by :py:func:`torchaudio.models.emformer_rnnt_base` The underlying model is constructed by :py:func:`torchaudio.models.emformer_rnnt_base`
and utilizes weights trained on TED-LIUM Release 3 dataset using training script ``train.py`` and utilizes weights trained on *TED-LIUM Release 3* :cite:`rousseau2012tedlium` dataset
`here <https://github.com/pytorch/audio/tree/main/examples/asr/emformer_rnnt>`__ with ``num_symbols=501``. using training script ``train.py``
`here <https://github.com/pytorch/audio/tree/main/examples/asr/emformer_rnnt>`__
with ``num_symbols=501``.
Please refer to :py:class:`torchaudio.pipelines.RNNTBundle` for usage instructions. Please refer to :py:class:`torchaudio.pipelines.RNNTBundle` for usage instructions.
""" """
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment