Deep-unlearning/kernels-community
Kernel sources for https://huggingface.co/kernels-community
Open Source Audio MLE at 🤗
Repositories
Deep-unlearning/nano-cohere-transcribe
Pure-PyTorch inference for CohereLabs/cohere-transcribe-03-2026 (2B Conformer + Transformer ASR, 14 languages).
Deep-unlearning/Finetune-Parakeet
Deep-unlearning/ARENA_3.0
Deep-unlearning/smol-audio
Practical, Colab-friendly notebooks for fine-tuning and running audio AI models
Deep-unlearning/finetune-gemma-audio
Deep-unlearning/hermes-agent
The agent that grows with you
Deep-unlearning/LLaSA_training
LLaSA: Scaling Train-time and Test-time Compute for LLaMA-based Speech Synthesis
Deep-unlearning/Finetune-AudioFlamingo3
Deep-unlearning/Finetune-Voxtral-ASR
Deep-unlearning/speech-to-speech
Build local voice agents with open-source models
Deep-unlearning/Learning-Audio-ML
Deep-unlearning/TTS-Audio-Suite
A ComfyUI custom node integration for multi-language High-quality Text-to-Speech and Voice Conversion nodes using multiple engines like RVC, ResembleAI's Chatterbox TTS, F5-TTS, Higgs Audio 2 and Microsoft VibeVoice with unlimited text length, SRT timing, Character support, Audio Analyzer, Silent Speech Analyzer, audio edit and more!!
Deep-unlearning/CosyVoice2-GRPO
A simple implementation for improving CosyVoice2 by GRPO method
Deep-unlearning/finetune-liquid-audio
Liquid Audio - Speech-to-Speech audio models by Liquid AI
Deep-unlearning/ddp_from_scratch
Deep-unlearning/Llasa-GRPO
Deep-unlearning/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Deep-unlearning/Deep-unlearning.github.io
Deep-unlearning/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Deep-unlearning/clawdbot
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Deep-unlearning/Qwen3-TTS
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
Deep-unlearning/torchtitan
A PyTorch native library for large model training
Deep-unlearning/Fun-ASR
Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.
Deep-unlearning/VoiceDiT
[ICASSP2025] Official code for VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis
Deep-unlearning/SmolVoice
Deep-unlearning/omnilingual-asr
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
Deep-unlearning/Finetune-Dia-TTS
Deep-unlearning/trl
Train transformer language models with reinforcement learning.