Melvin Vivas
melvindave
AI & ML interests
Small Language Models, Vision, TTS, STT, Image Gen
Recent Activity
updated a model about 18 hours ago
melvindave/gemma_4_legal_lora published a model about 18 hours ago
melvindave/gemma_4_legal_lora updated a dataset about 19 hours ago
melvindave/legal-synth-docsOrganizations
-
Qwen-3-VL-8B OCR Receipts
🚀1structured data parser from receipt images
-
Qwen3 Omni Demo
⚡262Chat with multimodal AI using text, audio, images, and video
-
VLM Object Understanding
🦀115Explore object detection, visual grounding, keypoint Detecti
-
Dataset Card Drafter
😻2Create dataset descriptions and open PRs automatically
-
VibeVoice-Realtime-0.5B
🐨184Generate natural speech from text with selectable voices
-
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 149k • 2.34k -
Qwen3 TTS Demo
🚀400Generate spoken audio from text in many voices and languages
-
mradermacher/Qwen3-1.7B-Multilingual-TTS-GGUF
2B • Updated • 4.35k • 10
-
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 4.87M • • 5.61k -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 6.88M • • 2.96k -
Whisper Large V3
🤫829Transcribe or translate audio and YouTube videos to text
-
Kugel Audio
👀90Generate natural-sounding speech in European languages with voice cloning
-
Qwen-3-VL-8B OCR Receipts
🚀1structured data parser from receipt images
-
Qwen3 Omni Demo
⚡262Chat with multimodal AI using text, audio, images, and video
-
VLM Object Understanding
🦀115Explore object detection, visual grounding, keypoint Detecti
-
Dataset Card Drafter
😻2Create dataset descriptions and open PRs automatically
-
VibeVoice-Realtime-0.5B
🐨184Generate natural speech from text with selectable voices
-
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 149k • 2.34k -
Qwen3 TTS Demo
🚀400Generate spoken audio from text in many voices and languages
-
mradermacher/Qwen3-1.7B-Multilingual-TTS-GGUF
2B • Updated • 4.35k • 10
-
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 4.87M • • 5.61k -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 6.88M • • 2.96k -
Whisper Large V3
🤫829Transcribe or translate audio and YouTube videos to text
-
Kugel Audio
👀90Generate natural-sounding speech in European languages with voice cloning