TTS
TTS copied to clipboard
[Bug] long text generation doesnt work
Describe the bug
try to generate anything beyond 250 words and it says
max token of 400
seems like the text splitter is not working
To Reproduce
try to generate anything beyond 250 words and it says
Expected behavior
text splitter splits it into segments of less than 250 and then recombine them
Logs
No response
Environment
{
"CUDA": {
"GPU": [
"NVIDIA GeForce RTX 3080"
],
"available": true,
"version": "11.8"
},
"Packages": {
"PyTorch_debug": false,
"PyTorch_version": "2.1.1+cu118",
"TTS": "0.21.1",
"numpy": "1.22.0"
},
"System": {
"OS": "Windows",
"architecture": [
"64bit",
"WindowsPE"
],
"processor": "AMD64 Family 25 Model 33 Stepping 2, AuthenticAMD",
"python": "3.10.11",
"version": "10.0.19045"
}
}
Additional context
No response
Any update on this? Came across a similar issue .. Also, does XTTS_v2 support long audio generations in general? How is the performance?
Its fixed
it takes 1 hour on a high end GPU to produce 2 hours. So very slow
Please inform me of interesting jobs and opportunities
From: aitechlab1 @.> Sent: Tuesday, December 12, 2023 11:08:36 PM To: coqui-ai/TTS @.> Cc: unifirer @.>; Author @.> Subject: Re: [coqui-ai/TTS] [Bug] long text generation doesnt work (Issue #3395)
Any update on this? Came across a similar issue .. Also, does XTTS_v2 support long audio generations in general? How is the performance?
β Reply to this email directly, view it on GitHubhttps://github.com/coqui-ai/TTS/issues/3395#issuecomment-1851726551, or unsubscribehttps://github.com/notifications/unsubscribe-auth/BEMJT2L6IUAAVFHCAZNG2BLYJAUKDAVCNFSM6AAAAABAOYNMXWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQNJRG4ZDMNJVGE. You are receiving this because you authored the thread.Message ID: @.***>
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discussion channels.