mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-11 06:55:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

minor fixes

Browse Source
This commit is contained in:
marcoyang 2023-06-28 17:25:42 +08:00
parent 34682d3b07
commit 3b3ada765c
7 changed files with 27 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/decoding-with-langugage-models/LODR.rst
View File

@ -45,7 +45,7 @@ Here, the source domain LM is trained on the training corpus. The only differenc
shallow fusion is the subtraction of the source domain LM. shallow fusion is the subtraction of the source domain LM.
Some works treat the predictor and the joiner of the neural transducer as its internal LM. However, the LM is Some works treat the predictor and the joiner of the neural transducer as its internal LM. However, the LM is
considered to be weak and can only capture low-level language information. Therefore, `LODR <https://arxiv.org/abs/2203.16776>`_ proposed to use considered to be weak and can only capture low-level language information. Therefore, `LODR <https://arxiv.org/abs/2203.16776>`__ proposed to use
a low-order n-gram LM as an approximation of the ILM of the neural transducer. This leads to the following formula a low-order n-gram LM as an approximation of the ILM of the neural transducer. This leads to the following formula
during decoding for RNNT model: during decoding for RNNT model:

10
docs/source/decoding-with-langugage-models/shallow-fusion.rst
View File

@ -24,7 +24,7 @@ to improve the word-error-rate of a RNN Transducer model.
We recommend you to use a GPU for decoding. We recommend you to use a GPU for decoding.
For illustration purpose, we will use a pre-trained ASR model from this `link <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29>`_. For illustration purpose, we will use a pre-trained ASR model from this `link <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29>`__.
If you want to train your model from scratch, please have a look at :ref:`non_streaming_librispeech_pruned_transducer_stateless`. If you want to train your model from scratch, please have a look at :ref:`non_streaming_librispeech_pruned_transducer_stateless`.
As the initial step, let's download the pre-trained model. As the initial step, let's download the pre-trained model.
@ -59,7 +59,7 @@ The following WERs are achieved on test-clean and test-other:
$ beam_size_4 7.93 best for test-other $ beam_size_4 7.93 best for test-other
These are already good numbers! But we can further improve it by using shallow fusion with external LM. These are already good numbers! But we can further improve it by using shallow fusion with external LM.
Training a language model usually takes a long time, we can download a pre-trained LM from this `link <https://huggingface.co/ezerhouni/icefall-librispeech-rnn-lm>`_. Training a language model usually takes a long time, we can download a pre-trained LM from this `link <https://huggingface.co/ezerhouni/icefall-librispeech-rnn-lm>`__.
.. code-block:: bash .. code-block:: bash
@ -72,8 +72,8 @@ Training a language model usually takes a long time, we can download a pre-train
.. note:: .. note::
This is an RNN LM trained on the LibriSpeech text corpus. So it might not be ideal for other corpus. This is an RNN LM trained on the LibriSpeech text corpus. So it might not be ideal for other corpus.
You may also train a RNN LM from scratch. Please refer to this `script <https://github.com/k2-fsa/icefall/blob/master/icefall/rnn_lm/train.py>`_ You may also train a RNN LM from scratch. Please refer to this `script <https://github.com/k2-fsa/icefall/blob/master/icefall/rnn_lm/train.py>`__
for training a RNN LM and this `script <https://github.com/k2-fsa/icefall/blob/master/icefall/transformer_lm/train.py>`_ to train a transformer LM. for training a RNN LM and this `script <https://github.com/k2-fsa/icefall/blob/master/icefall/transformer_lm/train.py>`__ to train a transformer LM.
To use shallow fusion for decoding, we can execute the following command: To use shallow fusion for decoding, we can execute the following command:
@ -141,7 +141,7 @@ A few parameters can be tuned to further boost the performance of shallow fusion
Here, we also show how `--beam-size` effect the WER and decoding time: Here, we also show how `--beam-size` effect the WER and decoding time:
.. list-table:: WERs and decoding time (on test-clean) of shallow fusion with different beam sizes .. list-table:: WERs and decoding time (on test-clean) of shallow fusion with different beam sizes
:widths: 25 25 50 :widths: 25 25 25 25
:header-rows: 1 :header-rows: 1
* - Beam size * - Beam size

6
docs/source/recipes/Non-streaming-ASR/librispeech/distillation.rst
View File

@ -13,7 +13,7 @@ for more details about MVQ-KD.
`pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`_. `pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`_.
Currently, we only implement MVQ-KD in this recipe. However, MVQ-KD is theoretically applicable to all recipes Currently, we only implement MVQ-KD in this recipe. However, MVQ-KD is theoretically applicable to all recipes
with only minor changes needed. Feel free to try out MVQ-KD in different recipes. If you with only minor changes needed. Feel free to try out MVQ-KD in different recipes. If you
encounter any problems, please open an issue here `icefall <https://github.com/k2-fsa/icefall/issues>`_. encounter any problems, please open an issue here `icefall <https://github.com/k2-fsa/icefall/issues>`__.
.. note:: .. note::
@ -217,7 +217,7 @@ the following command.
--exp-dir $exp_dir \ --exp-dir $exp_dir \
--enable-distillation True --enable-distillation True
You should get similar results as `here <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS-100hours.md#distillation-with-hubert>`_. You should get similar results as `here <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS-100hours.md#distillation-with-hubert>`__.
That's all! Feel free to experiment with your own setups and report your results. That's all! Feel free to experiment with your own setups and report your results.
If you encounter any problems during training, please open up an issue `here <https://github.com/k2-fsa/icefall/issues>`_. If you encounter any problems during training, please open up an issue `here <https://github.com/k2-fsa/icefall/issues>`__.

18
docs/source/recipes/Non-streaming-ASR/librispeech/pruned_transducer_stateless.rst
View File

@ -8,10 +8,10 @@ with the `LibriSpeech <https://www.openslr.org/12>`_ dataset.
.. Note:: .. Note::
The tutorial is suitable for `pruned_transducer_stateless <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless>`_, The tutorial is suitable for `pruned_transducer_stateless <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless>`__,
`pruned_transducer_stateless2 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless2>`_, `pruned_transducer_stateless2 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless2>`__,
`pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`_, `pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`__,
`pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless5>`_, `pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless5>`__,
We will take pruned_transducer_stateless4 as an example in this tutorial. We will take pruned_transducer_stateless4 as an example in this tutorial.
.. HINT:: .. HINT::
@ -237,7 +237,7 @@ them, please modify ``./pruned_transducer_stateless4/train.py`` directly.
.. NOTE:: .. NOTE::
The options for `pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/pruned_transducer_stateless5/train.py>`_ are a little different from The options for `pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/pruned_transducer_stateless5/train.py>`__ are a little different from
other recipes. It allows you to configure ``--num-encoder-layers``, ``--dim-feedforward``, ``--nhead``, ``--encoder-dim``, ``--decoder-dim``, ``--joiner-dim`` from commandline, so that you can train models with different size with pruned_transducer_stateless5. other recipes. It allows you to configure ``--num-encoder-layers``, ``--dim-feedforward``, ``--nhead``, ``--encoder-dim``, ``--decoder-dim``, ``--joiner-dim`` from commandline, so that you can train models with different size with pruned_transducer_stateless5.
@ -529,13 +529,13 @@ Download pretrained models
If you don't want to train from scratch, you can download the pretrained models If you don't want to train from scratch, you can download the pretrained models
by visiting the following links: by visiting the following links:
- `pruned_transducer_stateless <https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless-2022-03-12>`_ - `pruned_transducer_stateless <https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless-2022-03-12>`__
- `pruned_transducer_stateless2 <https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless2-2022-04-29>`_ - `pruned_transducer_stateless2 <https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless2-2022-04-29>`__
- `pruned_transducer_stateless4 <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless4-2022-06-03>`_ - `pruned_transducer_stateless4 <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless4-2022-06-03>`__
- `pruned_transducer_stateless5 <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless5-2022-07-07>`_ - `pruned_transducer_stateless5 <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless5-2022-07-07>`__
See `<https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS.md>`_ See `<https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS.md>`_
for the details of the above pretrained models for the details of the above pretrained models

4
docs/source/recipes/Streaming-ASR/introduction.rst
View File

@ -45,9 +45,9 @@ the input features.
We have three variants of Emformer models in ``icefall``. We have three variants of Emformer models in ``icefall``.
- ``pruned_stateless_emformer_rnnt2`` using Emformer from torchaudio, see `LibriSpeech recipe <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_stateless_emformer_rnnt2>`_. - ``pruned_stateless_emformer_rnnt2`` using Emformer from torchaudio, see `LibriSpeech recipe <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_stateless_emformer_rnnt2>`__.
- ``conv_emformer_transducer_stateless`` using ConvEmformer implemented by ourself. Different from the Emformer in torchaudio, - ``conv_emformer_transducer_stateless`` using ConvEmformer implemented by ourself. Different from the Emformer in torchaudio,
ConvEmformer has a convolution in each layer and uses the mechanisms in our reworked conformer model. ConvEmformer has a convolution in each layer and uses the mechanisms in our reworked conformer model.
See `LibriSpeech recipe <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conv_emformer_transducer_stateless>`_. See `LibriSpeech recipe <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conv_emformer_transducer_stateless>`__.
- ``conv_emformer_transducer_stateless2`` using ConvEmformer implemented by ourself. The only difference from the above one is that - ``conv_emformer_transducer_stateless2`` using ConvEmformer implemented by ourself. The only difference from the above one is that
it uses a simplified memory bank. See `LibriSpeech recipe <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conv_emformer_transducer_stateless2>`_. it uses a simplified memory bank. See `LibriSpeech recipe <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conv_emformer_transducer_stateless2>`_.

10
docs/source/recipes/Streaming-ASR/librispeech/pruned_transducer_stateless.rst
View File

@ -6,10 +6,10 @@ with the `LibriSpeech <https://www.openslr.org/12>`_ dataset.
.. Note:: .. Note::
The tutorial is suitable for `pruned_transducer_stateless <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless>`_, The tutorial is suitable for `pruned_transducer_stateless <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless>`__,
`pruned_transducer_stateless2 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless2>`_, `pruned_transducer_stateless2 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless2>`__,
`pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`_, `pruned_transducer_stateless4 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless4>`__,
`pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless5>`_, `pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless5>`__,
We will take pruned_transducer_stateless4 as an example in this tutorial. We will take pruned_transducer_stateless4 as an example in this tutorial.
.. HINT:: .. HINT::
@ -264,7 +264,7 @@ them, please modify ``./pruned_transducer_stateless4/train.py`` directly.
.. NOTE:: .. NOTE::
The options for `pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/pruned_transducer_stateless5/train.py>`_ are a little different from The options for `pruned_transducer_stateless5 <https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/pruned_transducer_stateless5/train.py>`__ are a little different from
other recipes. It allows you to configure ``--num-encoder-layers``, ``--dim-feedforward``, ``--nhead``, ``--encoder-dim``, ``--decoder-dim``, ``--joiner-dim`` from commandline, so that you can train models with different size with pruned_transducer_stateless5. other recipes. It allows you to configure ``--num-encoder-layers``, ``--dim-feedforward``, ``--nhead``, ``--encoder-dim``, ``--decoder-dim``, ``--joiner-dim`` from commandline, so that you can train models with different size with pruned_transducer_stateless5.

4
docs/source/recipes/Streaming-ASR/librispeech/zipformer_transducer.rst
View File

@ -6,7 +6,7 @@ with the `LibriSpeech <https://www.openslr.org/12>`_ dataset.
.. Note:: .. Note::
The tutorial is suitable for `pruned_transducer_stateless7_streaming <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless7_streaming>`_, The tutorial is suitable for `pruned_transducer_stateless7_streaming <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless7_streaming>`__,
.. HINT:: .. HINT::
@ -642,7 +642,7 @@ Download pretrained models
If you don't want to train from scratch, you can download the pretrained models If you don't want to train from scratch, you can download the pretrained models
by visiting the following links: by visiting the following links:
- `pruned_transducer_stateless7_streaming <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29>`_ - `pruned_transducer_stateless7_streaming <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29>`__
See `<https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS.md>`_ See `<https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/RESULTS.md>`_
for the details of the above pretrained models for the details of the above pretrained models