- https://www.youtube.com/@SyntheticVoices
- Joined on
Mar 05, 2023
SyntheticVoices closed issue mrq/ai-voice-cloning#406
selected index k out of range when attempting to gen more than 2 candidates
SyntheticVoices opened issue mrq/ai-voice-cloning#406
selected index k out of range when attempting to gen more than 2 candidates
SyntheticVoices opened issue mrq/ai-voice-cloning#401
Elevens Labs Adam Premade voice T-TTS/RVC model weights
SyntheticVoices commented on issue mrq/ai-voice-cloning#386
Implementing XTTS by coqui?> How strange, I did do some tests with XTTS's tokenizer but I didn't notice anything different. However, I did trigger some assertions when using `[{lang}] Text`, as it was trying to do redaction…
SyntheticVoices commented on issue mrq/ai-voice-cloning#386
Implementing XTTS by coqui?> Make sure you've updated tortoise-tts with: > > ``` > cd .\modules\tortoise-tts\ > git pull > ``` Yep it updated and I screwed up by not by downloading the Tokenizer correctly initally.…
SyntheticVoices commented on issue mrq/ai-voice-cloning#386
Implementing XTTS by coqui?``` Stored autoregressive model to settings: ./models/tortoise/autoregressive.pth Loading autoregressive model: ./models/tortoise/autoregressive.pth Traceback (most recent call last): File…
SyntheticVoices commented on issue mrq/ai-voice-cloning#386
Implementing XTTS by coqui?> Alrighty, I've converted the weights over and did some small tweaks to load it in TorToiSe. When it's uploaded, it'll be under https://huggingface.co/ecker/coqui-xtts. > > Samples (using…
SyntheticVoices commented on issue mrq/ai-voice-cloning#359
Are YouTube rips entirely unusable for finetuning?I use youtube all the time to train models. IMO if there is no background music don't bother with UVR.
SyntheticVoices closed issue mrq/ai-voice-cloning#326
WhisperX models (Large issue)
SyntheticVoices commented on issue mrq/ai-voice-cloning#326
WhisperX models (Large issue)\ai-voice-cloning\venv\lib\site-packages\faster_whisper\utils.py - I edited this file and just added a large on line 22 and that seems to have work. Just to check this was the correct thing to do?
SyntheticVoices opened issue mrq/ai-voice-cloning#326
WhisperX models (Large issue)
SyntheticVoices commented on issue mrq/ai-voice-cloning#319
Transcription and diarization (speaker identification) - Easy dataset building?> Did you successfully get a transcript from it? If not, do so, so you have a baseline for the output to expect. If so than simply replace primarySpeaker with your desired speaker when its looping…
SyntheticVoices commented on issue mrq/ai-voice-cloning#319
Transcription and diarization (speaker identification) - Easy dataset building?> > > > Long story short, I seem to have an issue with diarization not working that i need to sort out first > > > > > > I've been considering releasing a full dataset preparation pipeline for…
SyntheticVoices commented on issue mrq/ai-voice-cloning#319
Transcription and diarization (speaker identification) - Easy dataset building?> > Long story short, I seem to have an issue with diarization not working that i need to sort out first > > I've been considering releasing a full dataset preparation pipeline for tortoise but…
SyntheticVoices commented on issue mrq/ai-voice-cloning#319
Transcription and diarization (speaker identification) - Easy dataset building?Long story short, I seem to have an issue with diarization not working that i need to sort out first
SyntheticVoices commented on issue mrq/ai-voice-cloning#319
Transcription and diarization (speaker identification) - Easy dataset building?`import whisperx import torch import soundfile as sf import numpy as np def move_to_device(obj, device): if isinstance(obj, dict): return {key: move_to_device(value, device)…
SyntheticVoices commented on issue mrq/ai-voice-cloning#319
Transcription and diarization (speaker identification) - Easy dataset building?> > > It's supported by whisperx, see notes on [Speaker Diarization](https://github.com/m-bain/whisperX/blob/main/README.md#speaker-diarization) in the README. > > > > Thanks, but as far I can…
SyntheticVoices commented on issue mrq/ai-voice-cloning#319
Transcription and diarization (speaker identification) - Easy dataset building?> It's supported by whisperx, see notes on [Speaker Diarization](https://github.com/m-bain/whisperX/blob/main/README.md#speaker-diarization) in the README. Thanks, but as far I can understand…
SyntheticVoices commented on issue mrq/ai-voice-cloning#296
Audio artifacts/repetitive words after trainingrepetitive words are usually the audio and train.txt not matching...which happens a lot even with WhisperX