Skip to content
ModelListedExternal
Download

TTS FARMLINGUA Models

WavTokenizer for Farmlingua TTS Pipeline — High-quality neural audio tokenizer (codec) used in the Farmlingua Voice System for African farmers.

Sourcehuggingface.co/Remostartdev/TTS_FARMLINGUA-models/tree/b4c8d0d08f33689769ffdb574a19b2757e215e7b
KindOtherBase modelnovateur/WavTokenizer-large-320-24k-4096VersionWavtokenizer large speech 320 24kCgrade

Model source

Kind
Other
File size
1.63 GB
Base model
novateur/WavTokenizer-large-320-24k-4096
Version
vWavtokenizer large speech 320 24k
Updated
Oct 11, 2026
Source
Hugging Face

Source description

TTS_FARMLINGUA-models

WavTokenizer for Farmlingua TTS Pipeline — High-quality neural audio tokenizer (codec) used in the Farmlingua Voice System for African farmers.

This repository contains the WavTokenizer checkpoint + config used as the audio tokenizer in the Farmlingua multilingual TTS system (text-to-text + text-to-speech for farmers).

Model Details

  • Base Model: novateur/WavTokenizer-large-320-24k-4096
  • Architecture: WavTokenizer (Vocos backbone + single quantizer)
  • Sampling Rate: 24kHz
  • Tokens per second: 75
  • Use Case: Audio tokenization for TTS in low-resource African languages (Hausa, Yoruba, etc.)

How to Use (Direct Loading)

1. Install dependencies

pip install torch torchaudio
git clone https://github.com/jishengpeng/WavTokenizer.git
cd WavTokenizer
pip install -e .

Sources

1 source
Hugging FacePrimaryVersion b4c8d0d08f33689769ffdb574a19b2757e215e7b
huggingface.co/Remostartdev/TTS_FARMLINGUA-models/tree/b4c8d0d08f33689769ffdb574a19b2757e215e7b

Verified Oct 11

Model artifacts

1 artifact

wavtokenizer_large_speech_320_24k.ckpt

ckpt · 1.63 GB · SHA-256 7450020c154f…cc5a · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 2huggingface.co/Remostartdev/TTS_FARMLINGUA-models

--- license: apache-2.0 base_model: novateur/WavTokenizer-large-320-24k-4096 tags: - text-to-speech - tts - audio-codec - wavtokenizer - speech-to-text - asr - conversational - agriculture - farmers - african-languages - low-resource - farmlingua pipeline_tag: audio-to-audio --- # TTS_FARMLINGUA-models **WavTokenizer for Farmlingua TTS Pipeline** — High-quality neural audio tokenizer (codec) used in the Farmlingua Voice System for African farmers. This repository contains the **WavTokenizer** checkpoint + config used as the audio tokenizer in the Farmlingua multilingual TTS system (text-to-text + text-to-speech for farmers). ## Model Details - **Base Model**: [novateur/WavTokenizer-large-320-24k-4096](https://huggingface.co/novateur/WavTokenizer-large-320-24k-4096) - **Architecture**: WavTokenizer (Vocos backbone + single quantizer) - **Sampling Rate**: 24kHz - **Tokens per second**: 75 - **Use Case**: Audio tokenization for TTS in low-resource African languages (Hausa, Yoruba, etc.) ## How to Use (Direct Loading) ### 1. Install dependencies ```bash pip install torch torchaudio git clone https://github.com/jishengpeng/WavTokenizer.git cd WavTokenizer pip install -e .

NoteAug 2huggingface.co/Remostartdev/TTS_FARMLINGUA-models

Source context: 0 downloads · 0 likes · Pipeline audio-to-audio · Repo Remostartdev/TTS_FARMLINGUA-models