Ferramentas de IA

distil-whisper/distil-large-v3 — automatic-speech-recognition

MahmoudAshraf/mms-300m-1130-forced-aligner — automatic-speech-recognition

hubertsiuzdak/snac_24khz

FacebookAI/roberta-base — fill-mask

Qwen/Qwen2.5-7B-Instruct — text-generation

google-bert/bert-base-uncased — fill-mask

distilbert/distilbert-base-uncased — fill-mask

answerdotai/ModernBERT-base — fill-mask

FacebookAI/xlm-roberta-base — fill-mask

jonatasgrosman/wav2vec2-large-xlsr-53-russian — automatic-speech-recognition

Helsinki-NLP/opus-mt-tr-en — translation

openai/clip-vit-base-patch16 — zero-shot-image-classification

llava-hf/llava-1.5-7b-hf — image-text-to-text

openai-community/roberta-base-openai-detector — text-classification

daekeun-ml/koelectra-small-v3-nsmc — text-classification

google/vit-base-patch16-224 — image-classification

O AudioBot permite converter texto em fala com som natural para mídia e acessibilidade, produzindo facilmente áudio com mais de 500 vozes regionais e MP3s para download.

Meshy é uma ferramenta de modelagem 3D que permite aos usuários criar modelos detalhados a partir de prompts de texto e imagens. Ela suporta texturização personalizada, criação de personagens com rigging...

w11wo/indonesian-roberta-base-posp-tagger — token-classification

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 — text-generation

Qwen/Qwen2.5-VL-3B-Instruct — image-text-to-text

meta-llama/Meta-Llama-3-8B — text-generation

Qwen/Qwen2-VL-7B-Instruct — image-text-to-text

meta-llama/Llama-3.2-3B — text-generation