Visual Salamandra: Pushing the Boundaries of Multimodal Understanding
• 3
AI & ML interests
Language Modelling, Machine Translation, Speech Recognition and Synthesis, Biomedical NLP.
Recent Activity
Articles
pinned
Running
5
CATALAN ASR ARENA
🥇
Public ASR Arena leaderboard for Catalan ASR evaluations.
Running on Zero
Agents
1
SalamandraTAV
🌐
Speech-To-Text Tranlsation model in Iberic languages
Running
1
Asistente del Hotel
🏨
Book hotel rooms and get instant reservation help
Running
matxa-tts-v2
💻
Fast and lightweight central Catalan TTS
Sleeping
Agents
ASR UI
🤫
Transcribe audio and detect speaker details with two-step mode
Sleeping
Agents
SpeechSalamandra SQA
👁
Ask questions about speech utterances to Speech Salamandra.
Running on Zero
Agents
6
SalamandraTA 7B Demo
🦀
SalamandraTA-7B demo for translation.
Running
README
👀
Running on Zero
Agents
2
ASR UI
🤫
Transcribe audio and extract details
Sleeping
Agents
T45 Crexdata Demo
😻
Classify and analyze social media posts for flood and wildfire events
Runtime error
Agents
VECTOR STORE EADOP
🗂
Retrieve context based on a prompt and number of chunks
Runtime error
Agents
FLUX.1 [Schnell]
🏎
Generate images from text prompts
Runtime error
Seamless Streaming
📞