Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

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.

ArtOtherVersionRevision a473ec5CBewertung

Modellquelle

Art
Other
Dateigröße
714 MB
Version
vRevision a473ec5
Aktualisiert
19. Okt. 2026
Downloads
0
Quelle
Hugging Face

Quellenbeschreibung

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.

Files

filepurpose
kokoro_kannada_00005_inference.pthmodel weights (optimizer stripped, inference-ready)
config_kn.ymlStyleTTS2 architecture/config
ref_spk9.wavthe 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.

Quellen

1 Quelle
Hugging FacePrimärVersion a473ec5a48e61c0dc375d0463a3bf7a0e15e5467
huggingface.co/Sammy-Mohan/Kokoro-82M-Kannada/tree/a473ec5a48e61c0dc375d0463a3bf7a0e15e5467

Verifiziert 19. Okt.

Modellartefakte

1 Artefakt

kokoro_kannada_00005_inference.pth

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

Download file

Quellenauszüge

3 Auszüge

--- 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.

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

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