Update demo.py
Browse files
demo.py
CHANGED
|
@@ -323,7 +323,7 @@ user_guide_html = f"""
|
|
| 323 |
|
| 324 |
<p> This is run on a single RTX 3090. </p>
|
| 325 |
<p> These networks can only generate natural speech with correct intonations (i.e generating NSFW, non-speech sounds, stutters etc. doesn't work.) </p>
|
| 326 |
-
<p> I will gradually update here and ->
|
| 327 |
<p>Everything in this demo & the repo (coming soon) is experimental. The main idea is just playing around with different things to see what works when you're limited to training on a pair of RTX 3090s.</p>
|
| 328 |
<p>The data used for the english model is rough and pretty tough for any TTS model (think debates, real conversations, plus a little bit of cleaner professional performances). It mostly comes from public sources or third parties (no TOS signed). I'll probably write a blog post later with more details.</p>
|
| 329 |
<p>So far I focused on English and Russian, more can be covered.</p>
|
|
|
|
| 323 |
|
| 324 |
<p> This is run on a single RTX 3090. </p>
|
| 325 |
<p> These networks can only generate natural speech with correct intonations (i.e generating NSFW, non-speech sounds, stutters etc. doesn't work.) </p>
|
| 326 |
+
<p> I will gradually update here and -> <a href="https://github.com/Respaired/Project_Kalliope" target="_blank" style="color: #77abff;">Github</a> </p>
|
| 327 |
<p>Everything in this demo & the repo (coming soon) is experimental. The main idea is just playing around with different things to see what works when you're limited to training on a pair of RTX 3090s.</p>
|
| 328 |
<p>The data used for the english model is rough and pretty tough for any TTS model (think debates, real conversations, plus a little bit of cleaner professional performances). It mostly comes from public sources or third parties (no TOS signed). I'll probably write a blog post later with more details.</p>
|
| 329 |
<p>So far I focused on English and Russian, more can be covered.</p>
|