ModelPublicadoExterno

Kokoro 82M Kannada

Fast, small, open Kannada TTS: Kokoro-82M (distilled StyleTTS2) fine-tuned for Kannada with a trained diffusion prosody sampler — the component stock Kokoro drops, and the difference between robotic and natural prosody.

Fuentehuggingface.co/Sammy-Mohan/Kokoro-82M-Kannada/tree/a473ec5a48e61c0dc375d0463a3bf7a0e15e5467

TipoOtherVersiónRevision a473ec5Ccalidad

Fuente del modelo

Tipo: Other
Tamaño del archivo: 714 MB
Versión: vRevision a473ec5
Actualizado: 19 oct 2026
Descargas: 0
Fuente: Hugging Face

Descripción de la fuente

Kokoro-82M · Kannada (ಕನ್ನಡ)

Fast, small, open Kannada TTS: Kokoro-82M (distilled StyleTTS2) fine-tuned for Kannada with a trained diffusion prosody sampler — the component stock Kokoro drops, and the difference between robotic and natural prosody.

🔊 Samples: https://huggingface.co/spaces/Sammy-Mohan/kannada-tts
📖 Code, recipe & the full journey (all findings): https://github.com/sammy4321/Kokoro-Indic-Fine-Tuning

Files

file	purpose
`kokoro_kannada_00005_inference.pth`	model weights (optimizer stripped, inference-ready)
`config_kn.yml`	StyleTTS2 architecture/config
`ref_spk9.wav`	the style-reference clip = the shipped voice (full-bandwidth speaker — important, see repo)

Usage

Use the inference script (handles the fork's architecture code + diffusion sampling + best-of-N):

git clone https://github.com/sammy4321/Kokoro-Indic-Fine-Tuning
cd Kokoro-Indic-Fine-Tuning && pip install -r demo/requirements.txt huggingface_hub
python inference/synthesize.py --text "ನಮಸ್ಕಾರ!" --out out.wav --best-of 3

Details

82M params · 24 kHz · trained on ~11 h public Kannada speech (SPRINGLab IndicTTS + AI4Bharat Rasa, 17 speakers) for <$100 of compute. ASR round-trip CER 0.00 on clean text. Known gaps: numerals-as-digits and heavy English code-switching need a text-normalization frontend (roadmap).

License: code Apache-2.0; weights are derived from the datasets above — check their terms before commercial use; attribution required. Built on StyleTTS2 (MIT), Kokoro-82M (Apache-2.0), and the kikiri-tts recipe.

Fuentes

1 fuente

Hugging FacePrincipalVersión a473ec5a48e61c0dc375d0463a3bf7a0e15e5467

huggingface.co/Sammy-Mohan/Kokoro-82M-Kannada/tree/a473ec5a48e61c0dc375d0463a3bf7a0e15e5467

Verificado 19 oct

Artefactos del modelo

1 artefacto

kokoro_kannada_00005_inference.pth

pth · 714 MB · SHA-256 542798b1805a…c8ca · Hugging Face

Download file

Extractos de fuentes

3 extractos

Readme3 agohuggingface.co/Sammy-Mohan/Kokoro-82M-Kannada

--- language: kn license: apache-2.0 tags: [text-to-speech, tts, kannada, kokoro, styletts2] pipeline_tag: text-to-speech --- # Kokoro-82M · Kannada (ಕನ್ನಡ) Fast, small, open Kannada TTS: [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) (distilled StyleTTS2) fine-tuned for Kannada **with a trained diffusion prosody sampler** — the component stock Kokoro drops, and the difference between robotic and natural prosody. - 🔊 **Samples:** https://huggingface.co/spaces/Sammy-Mohan/kannada-tts - 📖 **Code, recipe & the full journey (all findings):** https://github.com/sammy4321/Kokoro-Indic-Fine-Tuning ## Files | file | purpose | |---|---| | `kokoro_kannada_00005_inference.pth` | model weights (optimizer stripped, inference-ready) | | `config_kn.yml` | StyleTTS2 architecture/config | | `ref_spk9.wav` | the style-reference clip = the shipped voice (full-bandwidth speaker — important, see repo) | ## Usage Use the inference script (handles the fork's architecture code + diffusion sampling + best-of-N): ```bash git clone https://github.com/sammy4321/Kokoro-Indic-Fine-Tuning cd Kokoro-Indic-Fine-Tuning && pip install -r demo/requirements.txt huggingface_hub python inference/synthesize.py --text "ನಮಸ್ಕಾರ!" --out out.wav --best-of 3 ``` ## Details 82M params · 24 kHz · trained on ~11 h public Kannada speech ([SPRINGLab IndicTTS](https://huggingface.co/datasets/SPRINGLab/IndicTTS_Kannada) + [AI4Bharat Rasa](https://huggingface.co/datasets/ai4bharat/Rasa), 17 speakers) for <$100 of compute. ASR round-trip CER 0.00 on clean text. Known gaps: numerals-as-digits and heavy English code-switching need a text-normalization frontend (roadmap). **License:** code Apache-2.0; weights are derived from the datasets above — check their terms before commercial use; attribution required. Built on StyleTTS2 (MIT), Kokoro-82M (Apache-2.0), and the [kikiri-tts](https://github.com/semidark/kikiri-tts) recipe.

Note19 octhuggingface.co/Sammy-Mohan/Kokoro-82M-Kannada

Source context: 0 downloads · 2 likes · Pipeline text-to-speech · Repo Sammy-Mohan/Kokoro-82M-Kannada

Note3 agohuggingface.co/Sammy-Mohan/Kokoro-82M-Kannada

Source context: 0 downloads · 1 likes · Pipeline text-to-speech · Repo Sammy-Mohan/Kokoro-82M-Kannada