doing something
ElevenLabs fine-tunes own models on your voice if you use PVC feature #vc #audio
In case, if someone wanted to clone my voice, here’s the files:
https://huggingface.co/datasets/Yehor/voice-cloning-elevenlabs
https://huggingface.co/datasets/Yehor/voice-cloning-elevenlabs
huggingface.co
Yehor/my-voice · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
😁1
Forwarded from Листи задрота
Европейський Союз запустив пілот децентралізованого веб-індексу який публікує пошуковий індекс. Це дозволить стороннім гравцям будувати свій пошуковий рушій поверх цих датасетів
👍1
doing something
In case, if someone wanted to clone my voice, here’s the files: https://huggingface.co/datasets/Yehor/voice-cloning-elevenlabs
doing something
Then helps to understand pronunciation for lip motion
This media is not supported in your browser
VIEW IN TELEGRAM
Some preprocessing in Audacity and CLI magic with a video note and we have a fake
doing something
A way to convert datasets from JSONL to DuckDB quickly. #duckdb
That example shows this dataset: https://huggingface.co/datasets/speech-uk/generated-news-comments
The same method was used to create a table for https://huggingface.co/datasets/speech-uk/voiced-news-comments dataset
DuckDB gives ability to fastly prototype
In the Speech-UK initiative these two datasets will be used to crowd-source data for Ukrainian ASR
Next step: create a Telegram bot using https://github.com/AmarnathCJD/gogram to make voice crowd-sourcing available to beta users
The same method was used to create a table for https://huggingface.co/datasets/speech-uk/voiced-news-comments dataset
DuckDB gives ability to fastly prototype
In the Speech-UK initiative these two datasets will be used to crowd-source data for Ukrainian ASR
Next step: create a Telegram bot using https://github.com/AmarnathCJD/gogram to make voice crowd-sourcing available to beta users