bond005/whisper-podlodka-turbo
Automatic Speech Recognition β’ 0.8B β’ Updated β’ 1.72k β’ 41
Explore and compare speechβrecognition model benchmarks
Generate custom scenes with your own character image
Generate customized images using text and multiple images
Flexible Photo Recrafting While Preserving Your Identity
StyleTTS2 trained on Ukrainian multispeaker dataset
Chat with an AI assistant (text and images)
Compare fast FLUX
Image Super-resolution via Diffusion Inversion
Scalable and Versatile 3D Generation from images
Fill and modify images using a mask and prompt
Generate customized images from text and reference photos
Personalised Podcasts For All - Available in 13 Languages