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