Spaces:

Akjava
/

matcha-tts-onnx-benchmarks

Running

Akjava commited on Sep 19, 2024

Commit

ccff356

verified ·

1 Parent(s): 0537f85

Update index.html

Files changed (1) hide show

index.html CHANGED Viewed

@@ -4,15 +4,13 @@
     <meta name="viewport" content="width=device-width" />
     <link rel="stylesheet" href="style.css" />
     <meta charset="UTF-8">
-    <title>Match-TTS Onnx En001-English</title>
 </head>
 <body>
-    <h1>Match-TTS Onnx En001-English(Faster GPU Version)</h1>
-    <div>this example using Quantized version(lowquality and slow) because of Github Page 100MB limitation</div>
-    <p><a href = "https://huggingface.co/Akjava/matcha_tts_common_voice_01_en_001">common_voice_01_en_001</a> - my trained model.you can create too!</p>
-    <br>
-    <script src="https://cdn.jsdelivr.net/npm/onnxruntime-web/dist/ort.webgpu.min.js" ></script>
     <script type="module">
         import { MatchaTTSRaw } from "./js-esm/matcha_tts_raw.js";

     <meta name="viewport" content="width=device-width" />
     <link rel="stylesheet" href="style.css" />
     <meta charset="UTF-8">
+    <title>Match-TTS Onnx Benchmarks</title>
 </head>
 <body>
+    <h1>Match-TTS Onnx Benchmarks</h1>
+    <div>Quantized version is too slow and just for Github Page 100MB limitation</div>
+    <div>Multispeaker(vctk) is littlebit slow than singlespeaker.en001 is littlg bit firster maybe timesteps is 5(bigger hq but slow)</div>
+    <div>almost load time 15 sec,infer time 2 sec(my 2070super-gpu)</div>
     <script type="module">
         import { MatchaTTSRaw } from "./js-esm/matcha_tts_raw.js";