In a Training Loop 🔄

2 53

Alain Galvan

alaingalvan

https://alain.xyz

AI & ML interests

Ray tracing denoisers, autoencoders.

Recent Activity

liked a Space 26 days ago

HuggingFaceM4/faster-qwen3-tts-demo

liked a Space about 1 month ago

nvidia/parakeet-tdt-0.6b-v2

liked a Space about 1 month ago

HuggingFaceTB/smol-training-playbook

View all activity

Organizations

None yet

liked a Space 26 days ago

faster-qwen3-tts

🎙

186

Generate spoken audio from text with custom or cloned voices

liked 3 Spaces about 1 month ago

Parakeet-TDT-0.6b-V2

467

Transcribe audio files with timestamps and download transcripts

The Smol Training Playbook

📚

3.06k

The secrets to building world-class LLMs

Parakeet STT Progressive Transcription

🎤

Transcribe speech to text instantly with WebGPU acceleration

liked a model about 1 month ago

openai/whisper-large-v3-turbo

Automatic Speech Recognition • Updated Oct 4, 2024 • 4.93M • • 2.87k

upvoted an article about 2 months ago

Article

Creating custom kernels for the AMD MI300

Jul 9, 2025

•

upvoted a paper about 2 months ago

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

Paper • 2108.01073 • Published Aug 2, 2021 • 9

liked a model about 2 months ago

zai-org/GLM-OCR

Image-to-Text • Updated 12 days ago • 3.42M • • 1.44k

liked 2 Spaces about 2 months ago

PaddleOCR-VL-1.5 Online Demo

😻

PaddleOCR-VL-1.5_Online_Demo

Qwen3-ASR Demo

🎙

115

Transcribe audio to text with multi-language timestamps

liked 2 models about 2 months ago

nvidia/personaplex-7b-v1

Audio-to-Audio • Updated 22 days ago • 269k • 2.32k

deepseek-ai/DeepSeek-OCR-2

Image-Text-to-Text • 3B • Updated Feb 3 • 1.24M • 878

liked 2 Spaces about 2 months ago

Whisper

📉

2.75k

Transcribe audio files into text

Omni Image Editor

🖼

1.25k

Image edit, text to image, image upscale, remove watermark

liked 2 models about 2 months ago

fal/flux-2-klein-4B-background-remove-lora

Image-to-Image • Updated Jan 21 • • 23

Supertone/supertonic-2

Text-to-Speech • Updated Jan 6 • 4.86k • 368

liked a Space 2 months ago

Qwen3-TTS Demo

🎙

1.74k

Generate speech audio via voice design, cloning, or preset speakers

liked 3 models 2 months ago