license: cc-by-nc-4.0
language:
- es
base_model:
- SWivid/F5-TTS
F5-TTS Spanish Language Model
Overview
The F5-TTS model is finetuned specifically for Spanish language speech synthesis. This project aims to deliver high-quality, regionally diverse speech synthesis capabilities for Spanish speakers.
License
This model is released under the CC0-1.0 license, which allows for free usage, modification, and distribution.
Datasets
The following datasets were used for training:
- Voxpopuli Dataset, with mainly Peninsular Spain accents
- Crowdsourced high-quality Spanish speech data:
- Argentinian Spanish
- Chilean Spanish
- Colombian Spanish
- Peruvian Spanish
- Puerto Rican Spanish
- Venezuelan Spanish
Additional sources:
- Crowdsourced high-quality Argentinian Spanish speech data set
- Crowdsourced high-quality Chilean Spanish speech data set
- Crowdsourced high-quality Colombian Spanish speech data set
- Crowdsourced high-quality Peruvian Spanish speech data set
- Crowdsourced high-quality Puerto Rico Spanish speech data set
- Crowdsourced high-quality Venezuelan Spanish speech data set
Model Information
Base Model: SWivid/F5-TTS
Total Training Duration: 218 hours of audio
Training Configuration:
- Batch Size: 3200
- Max Samples: 64
- Training Steps: 1,200,000
Usage Instructions
- Run the F5-TTS application and monitor the terminal output. The path to the model file will be displayed, similar to the following:
model : C:\Users\thega\.cache\huggingface\hub\models--SWivid--F5-TTS\snapshots\995ff41929c08ff968786b448a384330438b5cb6\F5TTS_Base\model_1200000.safetensors - Replace the Model File:
- Navigate to the specified location.
- Rename the existing file to
model_1200000.safetensors.bak. - Download the
model_1200000.safetensorsfile from this repository and place it in the same location.
- Rerun the application to load the updated model.
Contributions and Recommendations
This model may benefit from further fine-tuning to enhance its performance across different Spanish dialects. Contributions from the community are encouraged. For optimal output quality, preprocess the reference audio by removing background noise, balancing audio levels, and enhancing clarity.