Ir para o conteúdo
ModelListadosExterno
Baixar

Qwen2.5 Omni 3b Keyboard Video Text

Fine-tuned on video and audio of typing to predict the typed text.

TipoLoRAModelo baseQwen/Qwen2.5-Omni-3BVersãoFP32Cnota

Fonte do modelo

Tipo
LoRA
Tamanho do arquivo
173 MB
Modelo base
Qwen/Qwen2.5-Omni-3B
Versão
vFP32
Atualizado
30 de out. de 2026
Downloads
58
Fonte
Hugging Face

Descrição da fonte

Model Card for Qwen2.5-Omni-3B-Keyboard-Video-Text

Fine-tuned on video and audio of typing to predict the typed text.

Fontes

1 fonte
Hugging FacePrimárioVersão daf1c2948e1f51a3647983cc461c5f846b290577
huggingface.co/andrewt28/qwen2.5-omni-3b-keyboard-video-text/tree/daf1c2948e1f51a3647983cc461c5f846b290577

Verificado 30 de out.

Download files

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · FP32 (tensor header) · 173 MB · SHA-256 89ff93a49490…a0f7 · Hugging Face

Download file

Trechos de fonte

3 trechos

--- library_name: peft license: afl-3.0 datasets: - andrewt28/keystroke-typing-videos language: - en base_model: - Qwen/Qwen2.5-Omni-3B pipeline_tag: video-text-to-text --- # Model Card for Qwen2.5-Omni-3B-Keyboard-Video-Text Fine-tuned on video and audio of typing to predict the typed text.

Source context: 58 downloads · 0 likes · Pipeline video-text-to-text · Library peft · Repo andrewt28/qwen2.5-omni-3b-keyboard-video-text

Source context: 2 downloads · 0 likes · Pipeline video-text-to-text · Library peft · Repo andrewt28/qwen2.5-omni-3b-keyboard-video-text