mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-18 21:44:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

minor updates

Browse Source
This commit is contained in:
marcoyang1998 2023-07-27 11:49:34 +08:00
parent f05778b1ab
commit 3cecabdc84
2 changed files with 19 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
docs/source/decoding-with-langugage-models/index.rst
View File

@ -6,22 +6,23 @@ during decoding to improve the WER of transducer models.
The following decoding methods with external langugage models are available:
.. list-table:: Description of different decoding methods with external LM
.. list-table:: LM-rescoring-based methods vs shallow-fusion-based methods (The numbers in each field is WER on test-clean, WER on test-other and decoding time on test-clean)
:widths: 25 50
:header-rows: 1
* - Decoding method
- Description
* - `modified_beam_search`
- This one does not use language model. Beam search (i.e. really n-best decoding, the "beam" is the value of n), similar to the original RNN-T paper
* - `modified_beam_search_lm_shallow_fusion`
- As `modified_beam_search` but interpolate RNN-T scores with language model scores, also known as shallow fusion
* - `modified_beam_search_LODR`
- Low-order Density ratio. As `modified_beam_search_lm_shallow_fusion`, but subtract score of a (BPE-symbol-level) bigram backoff language model used as an approximation to the internal language model of RNN-T.
* - `modified_beam_search_lm_rescore`
- As `modified_beam_search`, but rescore the n-best hypotheses with external language model (e.g. RNNLM) and re-rank them.
* - `modified_beam_search_lm_rescore_LODR`
- As `modified_beam_search_lm_rescore`, but also subtract the score of a (BPE-symbol-level) bigram backoff language model during re-ranking.
- beam=4
* - ``modified_beam_search``
- Beam search (i.e. really n-best decoding, the "beam" is the value of n), similar to the original RNN-T paper. Note, this method does not use language model.
* - ``modified_beam_search_lm_shallow_fusion``
- As ``modified_beam_search``, but interpolate RNN-T scores with language model scores, also known as shallow fusion
* - ``modified_beam_search_LODR``
- As ``modified_beam_search_lm_shallow_fusion``, but subtract score of a (BPE-symbol-level) bigram backoff language model used as an approximation to the internal language model of RNN-T.
* - ``modified_beam_search_lm_rescore``
- As ``modified_beam_search``, but rescore the n-best hypotheses with external language model (e.g. RNNLM) and re-rank them.
* - ``modified_beam_search_lm_rescore_LODR``
- As ``modified_beam_search_lm_rescore``, but also subtract the score of a (BPE-symbol-level) bigram backoff language model during re-ranking.
.. toctree::

12
docs/source/decoding-with-langugage-models/rescoring.rst
View File

@ -4,7 +4,7 @@ LM rescoring for Transducer
=================================
LM rescoring is a commonly used approach to incorporate external LM information. Unlike shallow-fusion-based
methods (see :ref:`shallow-fusion`, :ref:`LODR`), rescoring is usually performed to re-rank the n-best hypotheses after beam search.
methods (see :ref:`shallow_fusion`, :ref:`LODR`), rescoring is usually performed to re-rank the n-best hypotheses after beam search.
Rescoring is usually more efficient than shallow fusion since less computation is performed on the external LM.
In this tutorial, we will show you how to use external LM to rescore the n-best hypotheses decoded from neural transducer models in
`icefall <https://github.com/k2-fsa/icefall>`__.
@ -225,23 +225,23 @@ Here, we benchmark the WERs and decoding speed of them:
- beam=4
- beam=8
- beam=12
* - `modified_beam_search`
* - ``modified_beam_search``
- 3.11/7.93; 132s
- 3.1/7.95; 177s
- 3.1/7.96; 210s
* - `modified_beam_search_lm_shallow_fusion`
* - ``modified_beam_search_lm_shallow_fusion``
- 2.77/7.08; 262s
- 2.62/6.65; 352s
- 2.58/6.65; 488s
* - LODR
* - ``modified_beam_search_LODR``
- 2.61/6.74; 400s
- 2.45/6.38; 610s
- 2.4/6.23; 870s
* - `modified_beam_search_lm_rescore`
* - ``modified_beam_search_lm_rescore``
- 2.93/7.6; 156s
- 2.67/7.11; 203s
- 2.59/6.86; 255s
* - `modified_beam_search_lm_rescore_LODR`
* - ``modified_beam_search_lm_rescore_LODR``
- 2.9/7.57; 160s
- 2.63/7.04; 203s
- 2.52/6.73; 263s