Andrés Marafioti

faster-qwen3-tts. Real-time text-to-speech with Qwen3-TTS

florence2-finetuning. Quick exploration into fine tuning florence 2

nano-parakeet. Pure-PyTorch Parakeet TDT inference

audioContextEncoder. A context encoder for audio inpainting

GACELA. Generative adversarial context encoder for audio inpainting

tifresi. STFT transforms suitable for use with PGHI (phase gradient heap integration)

not-human. The first CAPTCHA for bots. Prove you're not human.

phaseRetrievalEvaluation. Time-Frequency Phase Retrieval for Audio --- The Effect of Transform Parameters

speech-to-speech-inference-toolkit. Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.

qwenasr.cpp. Fast, installable Qwen3-ASR inference wrapper with CUDA-oriented backends

MeloTTS. High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

faster-qwen-asr. Python

AIAMI. Automatic Identification of Acoustical Musical Instruments

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

s2s-endpoint. Python

lightning-whisper-mlx. An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

smol-vision. Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

mlx-vlm. MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX.

smol-tools. Python

sagan-models. Python

waveInterferenceDemo. Demonstration of wave interference for the "Noise awareness day" at the Acoustics Research Institute in Vienna.

pydasp. Sistema diseñado para facilitar el maqueteado de efectos de audio.

pyside-tooltip. Python

scripts. Some scripts for easy sharing.

andimarafioti.

qwentts-cpp-python. Python bindings and wheel packaging for qwentts.cpp