<html><head><meta http-equiv="Content-Type" content="text/html charset=windows-1252"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">Hi Jean,<div class=""><br class=""></div><div class=""><br class=""><div><blockquote type="cite" class=""><div class=""><span style="font-family: Calibri; font-size: 16px;" class="">In the Scenario window I clicked on download and installed “[EN/H4W]Mouse” . Then I proceeded to the next window which is Speech Model where I clicked selected Open Model and clicked on download. I Installed “[EN/VF/HTK] Voxforge” and continued to the next two windows in which I left the default settings.</span> </div></blockquote>You mixed phoneme sets here. The EN/H4W mouse scenario uses the H4W phoneme set, while the EN/VF base model uses the VF phoneme set. Please use only matching scenario / base model configurations.<br class=""><blockquote type="cite" class=""><div class=""><div dir="ltr" style="font-family: Calibri; font-size: 16px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class=""><p class="MsoNormal" style="margin: 0in 0in 8pt; padding: 0px;"><o:p class=""></o:p></p><font face="Times New Roman" class=""></font><p class="MsoNormal" style="margin: 0in 0in 8pt; padding: 0px;">When I first activated Simon to test the “[EN/H4W]Mouse” Scenario, it wasn’t responding to the commands that it had.</p></div></div></blockquote>Yes, that would be expected behaviour. The H4W transcriptions are “foreign” to the VF base model, so it will remove those words from the language model (leaving none).</div><div><br class=""><blockquote type="cite" class=""><div class=""><div dir="ltr" style="font-family: Calibri; font-size: 16px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class=""><p class="MsoNormal" style="margin: 0in 0in 8pt; padding: 0px;"> I later created a Scenario of my own and used the first dictionary that can be seen in this link<span class="Apple-converted-space"> </span><a href="http://www.repository.voxforge1.org/downloads/Nightly_Builds/AcousticModel-2014-03-01/" class=""><font color="#0563c1" class="">http://www.repository.voxforge1.org/downloads/Nightly_Builds/AcousticModel-2014-03-01/</font></a><span class="Apple-converted-space"> </span>the one that ends with “<span style="line-height: 14.266666412353516px; font-family: CourierNewPSMT; font-size: 10pt;" class="">16kHz_16bit_MFCC_O_D.tgz</span><span style="line-height: 14.266666412353516px; font-size: 10pt;" class="">”</span><span style="line-height: 14.266666412353516px; font-family: CourierNewPSMT; font-size: 10pt;" class="">.</span></p></div></div></blockquote><div>That may be the right shadow dictionary. Voxforge slightly altered their transcription style at some point, though. Not sure when the base model was built - I think the dictionary should be fine, but if you run into problems it may be a good idea to try to use an earlier version of the Voxforge dictionary.</div><br class=""><blockquote type="cite" class=""><div class=""><div dir="ltr" style="font-family: Calibri; font-size: 16px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class=""><p class="MsoNormal" style="margin: 0in 0in 8pt; padding: 0px;"><span style="line-height: 14.266666412353516px; font-family: CourierNewPSMT; font-size: 10pt;" class=""><span class="Apple-converted-space"> </span></span><span class="">I was able to create a command that opened a Python command line using the “Trigger” button that can be found in the Grammar module when opening a Scenario. Trained the command that I used in the Scenario to open the Python command line 10 times but when I activated Simon it didn’t respond.<span class="Apple-converted-space"> </span></span></p></div></div></blockquote>You said you use a base model, right? From the tag, that is a Julius / HTK model. Training only has any effect if you either don’t use a base model or use an adapted base model. Did you use an adapted base model? There is no base model called “[EN/VF/HTK] Voxforge”. Did you use “[EN/VF/JHTK] Voxforge” or [EN/VF/JHTK] Voxforge Binary”?</div><div><br class=""><blockquote type="cite" class=""><div class=""><div dir="ltr" style="font-family: Calibri; font-size: 16px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class=""><p class="MsoNormal" style="margin: 0in 0in 8pt; padding: 0px;"><span class="">After training the Senerio that I created and trying to get it to work, this error started to appear everytime I tried activating Simon:</span></p></div></div></blockquote>Hm. Weird. Do these files exist when the error appears?</div><div>This is Simon 0.4.1, right?</div><div><br class=""></div><div>Best regards,</div><div>Peter</div><br class=""></div></body></html>