http://cslt.org/mediawiki/index.php?action=history&feed=atom&title=Mengyuan_Zhao_2015-12-14 2026-04-14T11:36:48Z 本wiki的该页面的版本历史 MediaWiki 1.23.3 http://cslt.org/mediawiki/index.php?title=Mengyuan_Zhao_2015-12-14&diff=18118&oldid=prev 2015-12-13T12:44:54Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2015年12月13日 (日) 12:44的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第2行：</td> <td colspan="2" class="diff-lineno">第2行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>*AM training on big dataset --mengyuan</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>*AM training on big dataset --mengyuan</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code.</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code.</div></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>:* Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse normal model.</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>:* Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse <ins class="diffchange diffchange-inline">than </ins>normal model.</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Start nnet3-ctc training on sinovoice 4000h 8k dataset.</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Start nnet3-ctc training on sinovoice 4000h 8k dataset.</div></td></tr> </table>

Zhaomy http://cslt.org/mediawiki/index.php?title=Mengyuan_Zhao_2015-12-14&diff=18117&oldid=prev 2015-12-13T12:44:35Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2015年12月13日 (日) 12:44的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第3行：</td> <td colspan="2" class="diff-lineno">第3行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code.</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code.</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse normal model.</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>:* Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse normal model.</div></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del class="diffchange diffchange-inline"> </del>* Start nnet3-ctc training on sinovoice 4000h 8k dataset.</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">:</ins>* Start nnet3-ctc training on sinovoice 4000h 8k dataset.</div></td></tr> </table>

Zhaomy http://cslt.org/mediawiki/index.php?title=Mengyuan_Zhao_2015-12-14&diff=18116&oldid=prev 2015-12-13T12:44:21Z

<p>以“==== RNN AM==== *AM training on big dataset --mengyuan :* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn&#039;t observe performance improvement. Ther...”为内容创建页面</p> <p><b>新页面</b></p><div>==== RNN AM====<br /> *AM training on big dataset --mengyuan<br /> :* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code.<br /> :* Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse normal model.<br /> * Start nnet3-ctc training on sinovoice 4000h 8k dataset.</div>

Zhaomy