Models
Open-source models for ML research and development, published on Hugging Face.
- DiffusionGemma 26B A4B IT — HERETIC (Uncensored)Abliterated, uncensored fine-tune of Google's diffusion_gemma 26B MoE model for text generation.
- OmniVoice BR-PT v1.5Brazilian Portuguese text-to-speech checkpoint fine-tuned from k2-fsa/OmniVoice.
- Whisper Large Hebrew Fine-tuneWhisper large fine-tuned on Hebrew speech from the Whisper Fine-Tuning Event, trained on google/fleurs.
- MiraTTS HindiQwen2-based text-to-speech model fine-tuned for Hindi from YatharthS/MiraTTS.
- Fish Speech Hindi LoRALoRA adapter for Fish Speech (dual_ar architecture) adapted for Hindi speech synthesis.
- Qwen3-8B TritonQwen3-8B fine-tune for generating Triton kernel code, trained on English and Chinese data.