deviandice

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…

2023-03-29 00:13:35 +07:00

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…

2023-03-28 13:48:56 +07:00

deviandice commented on issue mrq/ai-voice-cloning#85

Long prompts and random voice

Each 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.

2023-03-07 16:59:22 +07:00

deviandice commented on issue mrq/ai-voice-cloning#61

Memory Leak

Cuda 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…

2023-03-07 14:24:00 +07:00

deviandice opened issue mrq/ai-voice-cloning#84

20% Inference Speed increase for Large VRAM (3090+) GPUS

2023-03-07 14:13:34 +07:00

deviandice pushed to main at deviandice/tortoise-tts

e650800447 Update 'tortoise/utils/device.py'

2023-03-07 14:05:29 +07:00

deviandice created repository deviandice/tortoise-tts

2023-03-07 12:56:58 +07:00

deviandice created repository deviandice/ai-voice-cloning

2023-03-07 12:55:45 +07:00

deviandice commented on issue mrq/ai-voice-cloning#78

Implement BigVGAN Full Fat

There'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":…

2023-03-07 11:23:53 +07:00

deviandice opened issue mrq/ai-voice-cloning#78

Implement BigVGAN Full Fat

2023-03-06 23:43:00 +07:00

deviandice commented on issue mrq/ai-voice-cloning#74

Issues with einops on Windows

You 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…

2023-03-06 15:55:39 +07:00

deviandice commented on issue mrq/ai-voice-cloning#59

Set Whisper default to Base-EN

Yeah that sounds like a good middle ground. It's only the english model that get's this benefit anyway.

2023-03-05 03:03:46 +07:00

deviandice created repository deviandice/DL-Art-School

2023-03-04 17:56:14 +07:00

deviandice opened issue mrq/ai-voice-cloning#59

Set Whisper default to Base-EN

2023-03-04 01:27:34 +07:00

deviandice commented on issue mrq/ai-voice-cloning#52

Implement BigVGAN