Kani-TTS 400M v0.3 (Turkish Fine-tuned)

This model is a Turkish fine-tuned version of Kani-TTS 400M, adapted to the Turkish language using custom multi-speaker speech data collected from publicly available YouTube channels.

The primary goal of this fine-tuning is to improve Turkish pronunciation, prosody, and naturalness, enabling the base model to speak Turkish fluently.


🔊 Training Data

The training data was prepared via YouTube scraping and manual preprocessing (audio segmentation, cleaning, and transcript alignment).

🎤 Speakers

Speaker Tag Source Channel Gender Duration
sıla https://www.youtube.com/@BirDinle Female ~33 hours
taha https://www.youtube.com/@seslifikiristasyonu Male ~28 hours
  • Total duration: ~61 hours
  • Language: Turkish (tr-TR)
  • Domain: Narration / voice-over style speech

Speaker tags are explicitly used during training to enable multi-speaker inference.


🧠 Training Details

  • Base model: Kani-TTS 400M
  • Training type: Fine-tuning
  • Objective:
    • Improve Turkish language capability
    • Adapt pronunciation and phoneme alignment
    • Preserve speaker identity via speaker tags
  • Data source: Publicly available YouTube content
  • Audio length: ~3s – 20s segments

📜 License & Usage Notice (Academic / Non-Commercial)

This model is released strictly for academic research and experimental purposes.

  • The model is not intended for commercial use.
  • Commercial deployment, resale, or use in revenue-generating products or services is explicitly prohibited without prior permission.
  • The training data was derived from publicly accessible online sources and was used for research and educational objectives only.
  • Users are responsible for ensuring compliance with applicable laws, platform terms, and ethical guidelines when using this model.

By using this model, you agree that it is provided “as-is”, without warranties of any kind, and solely for non-commercial academic use.

Downloads last month
29
Safetensors
Model size
0.4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support