A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.
Repository Index
87,573 visible repositories in the index
1–12 of 12 · Most stars
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
- ai
- amd-gpu
- apple-silicon
- asr
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
10x faster matrix and vector operations
- machine-learning
- data-mining
- database
- compression
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters
Deep learning in Rust, with shape checked tensors and neural networks
- rust
- autograd
- autodiff
- machine-learning
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.
- audio
- audio-compression
- compression-algorithm
- deep-learning
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
Simple shell script to use OpenAI's ChatGPT and DALL-E from the terminal. No Python or JS required.
- chatbot
- chatgpt
- chatgpt-api
- chatgpt-api-wrapper
Translated涛声 (TaoSheng, "sound of waves"): use a single Android phone to record audio all day → transcribe → identify speakers → AI organizes it into to-dos and memories. No extra hardware, no account needed, and the data stays only on your phone.
- ai
- android
- jetpack-compose
- kotlin
The repository host gives no description.