mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 01:52:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

deploy: eef47adee9aa765f41cd63a8d57049b02849f3ad

Browse Source
This commit is contained in:
csukuangfj 2023-10-19 14:55:39 +00:00
parent 900bad65d3
commit 4ed40bc647
5 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
_sources/decoding-with-langugage-models/LODR.rst.txt
View File

@ -56,7 +56,7 @@ during decoding for transducer model:
\lambda_1 \log p_{\text{Target LM}}\left(y_u|\mathit{x},y_{1:u-1}\right) - \lambda_1 \log p_{\text{Target LM}}\left(y_u|\mathit{x},y_{1:u-1}\right) -
\lambda_2 \log p_{\text{bi-gram}}\left(y_u|\mathit{x},y_{1:u-1}\right) \lambda_2 \log p_{\text{bi-gram}}\left(y_u|\mathit{x},y_{1:u-1}\right)
In LODR, an additional bi-gram LM estimated on the source domain (e.g training corpus) is required. Comared to DR, In LODR, an additional bi-gram LM estimated on the source domain (e.g training corpus) is required. Compared to DR,
the only difference lies in the choice of source domain LM. According to the original `paper <https://arxiv.org/abs/2203.16776>`_, the only difference lies in the choice of source domain LM. According to the original `paper <https://arxiv.org/abs/2203.16776>`_,
LODR achieves similar performance compared DR in both intra-domain and cross-domain settings. LODR achieves similar performance compared DR in both intra-domain and cross-domain settings.
As a bi-gram is much faster to evaluate, LODR is usually much faster. As a bi-gram is much faster to evaluate, LODR is usually much faster.

2
_sources/model-export/export-ncnn-conv-emformer.rst.txt
View File

@ -125,7 +125,7 @@ Python code. We have also set up ``PATH`` so that you can use
.. caution:: .. caution::
Please don't use `<https://github.com/tencent/ncnn>`_. Please don't use `<https://github.com/tencent/ncnn>`_.
We have made some modifications to the offical `ncnn`_. We have made some modifications to the official `ncnn`_.
We will synchronize `<https://github.com/csukuangfj/ncnn>`_ periodically We will synchronize `<https://github.com/csukuangfj/ncnn>`_ periodically
with the official one. with the official one.

2
decoding-with-langugage-models/LODR.html
View File

@ -136,7 +136,7 @@ during decoding for transducer model:</p>
\log p_{rnnt}\left(y_u|\mathit{x},y_{1:u-1}\right) + \log p_{rnnt}\left(y_u|\mathit{x},y_{1:u-1}\right) +
\lambda_1 \log p_{\text{Target LM}}\left(y_u|\mathit{x},y_{1:u-1}\right) - \lambda_1 \log p_{\text{Target LM}}\left(y_u|\mathit{x},y_{1:u-1}\right) -
\lambda_2 \log p_{\text{bi-gram}}\left(y_u|\mathit{x},y_{1:u-1}\right)\]</div> \lambda_2 \log p_{\text{bi-gram}}\left(y_u|\mathit{x},y_{1:u-1}\right)\]</div>
<p>In LODR, an additional bi-gram LM estimated on the source domain (e.g training corpus) is required. Comared to DR, <p>In LODR, an additional bi-gram LM estimated on the source domain (e.g training corpus) is required. Compared to DR,
the only difference lies in the choice of source domain LM. According to the original <a class="reference external" href="https://arxiv.org/abs/2203.16776">paper</a>, the only difference lies in the choice of source domain LM. According to the original <a class="reference external" href="https://arxiv.org/abs/2203.16776">paper</a>,
LODR achieves similar performance compared DR in both intra-domain and cross-domain settings. LODR achieves similar performance compared DR in both intra-domain and cross-domain settings.
As a bi-gram is much faster to evaluate, LODR is usually much faster.</p> As a bi-gram is much faster to evaluate, LODR is usually much faster.</p>

2
model-export/export-ncnn-conv-emformer.html
View File

@ -226,7 +226,7 @@ Python code. We have also set up <code class="docutils literal notranslate"><spa
<div class="admonition caution"> <div class="admonition caution">
<p class="admonition-title">Caution</p> <p class="admonition-title">Caution</p>
<p>Please don’t use <a class="reference external" href="https://github.com/tencent/ncnn">https://github.com/tencent/ncnn</a>. <p>Please don’t use <a class="reference external" href="https://github.com/tencent/ncnn">https://github.com/tencent/ncnn</a>.
We have made some modifications to the offical <a class="reference external" href="https://github.com/tencent/ncnn">ncnn</a>.</p> We have made some modifications to the official <a class="reference external" href="https://github.com/tencent/ncnn">ncnn</a>.</p>
<p>We will synchronize <a class="reference external" href="https://github.com/csukuangfj/ncnn">https://github.com/csukuangfj/ncnn</a> periodically <p>We will synchronize <a class="reference external" href="https://github.com/csukuangfj/ncnn">https://github.com/csukuangfj/ncnn</a> periodically
with the official one.</p> with the official one.</p>
</div> </div>

2
searchindex.js
View File

File diff suppressed because one or more lines are too long