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: a5bbfc6f7eea68ac2602bf1cb271c1373cd43ed6

Browse Source
This commit is contained in:
csukuangfj 2023-05-19 08:22:40 +00:00
parent c7c0b4999a
commit 56d5535e7c
3 changed files with 19 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
_sources/model-export/export-ncnn-zipformer.rst.txt
View File

@ -276,7 +276,7 @@ The result looks like below:
7767517
2029 2547
SherpaMetaData sherpa_meta_data1 0 0 0=2 1=32 2=4 3=7 -23316=5,2,4,3,2,4 -23317=5,384,384,384,384,384 -23318=5,192,192,192,192,192 -23319=5,1,2,4,8,2 -23320=5,31,31,31,31,31
SherpaMetaData sherpa_meta_data1 0 0 0=2 1=32 2=4 3=7 15=1 -23316=5,2,4,3,2,4 -23317=5,384,384,384,384,384 -23318=5,192,192,192,192,192 -23319=5,1,2,4,8,2 -23320=5,31,31,31,31,31
Input in0 0 1 in0
**Explanation**
@ -300,6 +300,9 @@ The result looks like below:
- ``3=7``, 3 is the key and 7 is the value of for the amount of padding
used in the Conv2DSubsampling layer. It should be 7 for zipformer
if you don't change zipformer.py.
- ``15=1``, attribute 15, this is the model version. Starting from
`sherpa-ncnn`_ v2.0, we require that the model version has to
be >= 1.
- ``-23316=5,2,4,3,2,4``, attribute 16, this is an array attribute.
It is attribute 16 since -23300 - (-23316) = 16.
The first element of the array is the length of the array, which is 5 in our case.
@ -338,6 +341,8 @@ The result looks like below:
+----------+--------------------------------------------+
| 3 | 7 (if you don't change code) |
+----------+--------------------------------------------+
| 15 | 1 (The model version) |
+----------+--------------------------------------------+
|-23316 | ``--num-encoder-layer`` |
+----------+--------------------------------------------+
|-23317 | ``--encoder-dims`` |

18
model-export/export-ncnn-zipformer.html
View File

@ -432,7 +432,7 @@ this layer.</p></li>
The result looks like below:</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="m">7767517</span>
<span class="m">2029</span><span class="w"> </span><span class="m">2547</span>
SherpaMetaData<span class="w"> </span>sherpa_meta_data1<span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="nv">0</span><span class="o">=</span><span class="m">2</span><span class="w"> </span><span class="nv">1</span><span class="o">=</span><span class="m">32</span><span class="w"> </span><span class="nv">2</span><span class="o">=</span><span class="m">4</span><span class="w"> </span><span class="nv">3</span><span class="o">=</span><span class="m">7</span><span class="w"> </span>-23316<span class="o">=</span><span class="m">5</span>,2,4,3,2,4<span class="w"> </span>-23317<span class="o">=</span><span class="m">5</span>,384,384,384,384,384<span class="w"> </span>-23318<span class="o">=</span><span class="m">5</span>,192,192,192,192,192<span class="w"> </span>-23319<span class="o">=</span><span class="m">5</span>,1,2,4,8,2<span class="w"> </span>-23320<span class="o">=</span><span class="m">5</span>,31,31,31,31,31
SherpaMetaData<span class="w"> </span>sherpa_meta_data1<span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="nv">0</span><span class="o">=</span><span class="m">2</span><span class="w"> </span><span class="nv">1</span><span class="o">=</span><span class="m">32</span><span class="w"> </span><span class="nv">2</span><span class="o">=</span><span class="m">4</span><span class="w"> </span><span class="nv">3</span><span class="o">=</span><span class="m">7</span><span class="w"> </span><span class="nv">15</span><span class="o">=</span><span class="m">1</span><span class="w"> </span>-23316<span class="o">=</span><span class="m">5</span>,2,4,3,2,4<span class="w"> </span>-23317<span class="o">=</span><span class="m">5</span>,384,384,384,384,384<span class="w"> </span>-23318<span class="o">=</span><span class="m">5</span>,192,192,192,192,192<span class="w"> </span>-23319<span class="o">=</span><span class="m">5</span>,1,2,4,8,2<span class="w"> </span>-23320<span class="o">=</span><span class="m">5</span>,31,31,31,31,31
Input<span class="w"> </span>in0<span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="m">1</span><span class="w"> </span>in0
</pre></div>
</div>
@ -459,6 +459,9 @@ parameter <code class="docutils literal notranslate"><span class="pre">--num-lef
<li><p><code class="docutils literal notranslate"><span class="pre">3=7</span></code>, 3 is the key and 7 is the value of for the amount of padding
used in the Conv2DSubsampling layer. It should be 7 for zipformer
if you don’t change zipformer.py.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">15=1</span></code>, attribute 15, this is the model version. Starting from
<a class="reference external" href="https://github.com/k2-fsa/sherpa-ncnn">sherpa-ncnn</a> v2.0, we require that the model version has to
be &gt;= 1.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">-23316=5,2,4,3,2,4</span></code>, attribute 16, this is an array attribute.
It is attribute 16 since -23300 - (-23316) = 16.
The first element of the array is the length of the array, which is 5 in our case.
@ -505,19 +508,22 @@ will be <code class="docutils literal notranslate"><span class="pre">SAD</span><
<tr class="row-odd"><td><p>3</p></td>
<td><p>7 (if you don’t change code)</p></td>
</tr>
<tr class="row-even"><td><p>-23316</p></td>
<tr class="row-even"><td><p>15</p></td>
<td><p>1 (The model version)</p></td>
</tr>
<tr class="row-odd"><td><p>-23316</p></td>
<td><p><code class="docutils literal notranslate"><span class="pre">--num-encoder-layer</span></code></p></td>
</tr>
<tr class="row-odd"><td><p>-23317</p></td>
<tr class="row-even"><td><p>-23317</p></td>
<td><p><code class="docutils literal notranslate"><span class="pre">--encoder-dims</span></code></p></td>
</tr>
<tr class="row-even"><td><p>-23318</p></td>
<tr class="row-odd"><td><p>-23318</p></td>
<td><p><code class="docutils literal notranslate"><span class="pre">--attention-dims</span></code></p></td>
</tr>
<tr class="row-odd"><td><p>-23319</p></td>
<tr class="row-even"><td><p>-23319</p></td>
<td><p><code class="docutils literal notranslate"><span class="pre">--zipformer-downsampling-factors</span></code></p></td>
</tr>
<tr class="row-even"><td><p>-23320</p></td>
<tr class="row-odd"><td><p>-23320</p></td>
<td><p><code class="docutils literal notranslate"><span class="pre">--cnn-module-kernels</span></code></p></td>
</tr>
</tbody>

2
searchindex.js
View File

File diff suppressed because one or more lines are too long