Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
html,
body {
width: 100%;
height: 100%;
}
html > body {
overflow: hidden;
min-width: 1280px;
max-width: 1920px;
margin: 0 auto;
-webkit-transform: translate3d(0, 0, 0);
transform: translate3d(0, 0, 0);
}
p {
padding: 0;
margin: 0;
}
ul,
li {
margin: 0;
padding: 0;
}
li {
list-style: none;
}
a {
text-decoration: none;
}
input,
button,
textarea {
outline: none;
border: none;
}
textarea {
resize: none;
}
img {
border: none;
vertical-align: middle;
}
.ellipsis {
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
.xmgl-icon {
line-height: 1;
}
.app-container {
width: 100%;
height: 100%;
background-color: #eff2f6;
.app-content{
width: 100%;
height: 100%;
}
}
.page-container {
width: 100%;
padding: p(15);
.page-title {
padding-top: p(45);
padding-bottom: p(35);
font-size: p(40);
font-weight: 700;
color: #333333;
text-align: center;
}
}
.page-content {
width: p(1200);
background-color: #ffffff;
margin: 0 auto;
box-shadow: 0 1px 0 0 rgba(178, 188, 198, 0.51);
}
.page-list-content {
background-color: #ffffff;
box-shadow: 0 1px 0 0 rgba(178, 188, 198, 0.51);
}