ControlAltAI TTS/Talking Model | RVC 2 Mangio Crepe 500 Epochs

Created: February 6, 2024
ControlAltAI TTS/Talking Model | RVC 2 Mangio Crepe 500 Epochs

Trained with 12 minutes dataset using Mangio Crepe. High quality talking or TTS model from one of the narrator at ControlAltAI. For people who don't want to read long texts and just wants to convert long texts into audio. This model offers high quality speech with almost no tearing or robotic sibilances and offers clear pronunciation of words.

Dataset Info:
- No Breathes
- 40Khz Sample Rate
- 250 Hz Average Pitch Frequency Spoken
- High Pitch Female Voice

Training Settings:
- Mangio Crepe
- 8 Hop Length
- 20 Batch Size
- 500 Epochs
- 40K Sample Rate
- Normal V2 Pretrain

Model Link:
https://huggingface.co/SCRFilms/invoke/resolve/main/Invoke.zip?download=true

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/SCRFilms/invoke/resolve/main/Invoke.zip?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Sample deck

Pitch previews

Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.

samples ready
female base 路 pitch 0 Generated female reference sample
Run
male
female
female-base generated sample male-base generated sample Enrichment pending: no scores or voice accords yet Ctrl/Cmd-click = select multiple pitches