deviandice commented on issue mrq/ai-voice-cloning#152
VALL-E Integration (and In Response To TorToiSe: a Quick Retrospective)> And you can only really get good compute with Ada cards (4070Ti and up) or multiple Ampere cards I mean if that's the case I'll have a second 3090 with NVLINK sometime next month, so maybe…
deviandice commented on issue mrq/ai-voice-cloning#152
VALL-E Integration (and In Response To TorToiSe: a Quick Retrospective)> For zero-shot inferencing applications, diversity (ick) is a HUGE factor in having a good model. There's only so much data to sample from when trying to mimic voices. I worry that when I finally…
deviandice commented on issue mrq/ai-voice-cloning#85
Long prompts and random voiceEach new line restarts the voice process. IMO, if you find a line you like, you should use that as your voice. Otherwise you're asking a complete system rework.
deviandice commented on issue mrq/ai-voice-cloning#61
Memory LeakCuda can keep things cached, I have torch.cuda.empty_cache() added to get_device so it trigger's every time the TTS system is reloaded. Supposedly stuff can remained cached, which can cause weird…
deviandice opened issue mrq/ai-voice-cloning#84
20% Inference Speed increase for Large VRAM (3090+) GPUSdeviandice pushed to main at deviandice/tortoise-tts
- e650800447 Update 'tortoise/utils/device.py'
deviandice created repository deviandice/tortoise-tts
deviandice created repository deviandice/ai-voice-cloning
deviandice commented on issue mrq/ai-voice-cloning#78
Implement BigVGAN Full FatThere's a seperate config file for it. Here's the raw JSON. Also, funny joke ;) ``` config.json { "resblock": "1", "num_gpus": 0, "batch_size": 32, "learning_rate":…
deviandice opened issue mrq/ai-voice-cloning#78
Implement BigVGAN Full Fatdeviandice commented on issue mrq/ai-voice-cloning#74
Issues with einops on WindowsYou can jury rig it a bit. It's to do with whisperX. If you're not using it just do the following in powershell. Had the same issue on linux and this worked for me. ``` ./venv/scripts/activate…
deviandice commented on issue mrq/ai-voice-cloning#59
Set Whisper default to Base-ENYeah that sounds like a good middle ground. It's only the english model that get's this benefit anyway.
deviandice created repository deviandice/DL-Art-School
deviandice opened issue mrq/ai-voice-cloning#59
Set Whisper default to Base-ENdeviandice commented on issue mrq/ai-voice-cloning#52
Implement BigVGANThanks for implementing this so quickly, and its pretty neato that it's having a noticeable effect.
deviandice commented on issue mrq/ai-voice-cloning#3
FileNotFoundError immediately after starting trainingI had this error on windows. I fixed it by dropping ffmpeg.exe into the root folder of the repo.