yqxtqymn commented on issue mrq/ai-voice-cloning#80
CVVP latents missingI tried it before and it wasn't working for some reason. Anyway it's working now. Thanks! :)
yqxtqymn commented on issue mrq/ai-voice-cloning#80
CVVP latents missingI appreciate the detailed response. Was not aware support got dropped in the original Tortoise. CVVP impact is small, but it's a nice to have and play around with when you're trying to get a…
yqxtqymn commented on issue mrq/ai-voice-cloning#80
CVVP latents missingWhy shouldn't I use CVVP? I had some good generations with it in the 0.8-1 range.
yqxtqymn opened issue mrq/ai-voice-cloning#86
The number of rows in your dataset is greater than the maximum allowed (5000)
yqxtqymn commented on issue mrq/ai-voice-cloning#61
Memory LeakSpent some time trying to track the leak, I believe there's more than one. Under ai-voice-cloning/tortoise-tts/tortoise/api.py load_autoregressive_model ``` if hasattr(self,…
yqxtqymn pushed to master at yqxtqymn/ai-voice-cloning
-
1e2436aac9 Update 'src/utils.py'
yqxtqymn commented on issue mrq/ai-voice-cloning#45
Feature Request: Use WhisperX instead of Whisper for preparing datasetVery impressed with whisperx. Added a pr https://git.ecker.tech/mrq/ai-voice-cloning/pulls/67
yqxtqymn pushed to master at yqxtqymn/ai-voice-cloning
-
yqxtqymn pushed to master at yqxtqymn/ai-voice-cloning
-
yqxtqymn pushed to master at yqxtqymn/ai-voice-cloning
-
yqxtqymn pushed to master at yqxtqymn/ai-voice-cloning
-
yqxtqymn created repository yqxtqymn/ai-voice-cloning