inesc-id

This model is a fine-tuned Whisper variant of `openai/whisper-large-v3`, trained for European Portuguese (EP) (around 425h) automatic speech recognition (ASR). From CAMÕES work. --- 🧠 Model Description - Base model: `openai/whisper-large-v3` - Architecture: Transformer encoder–decoder - Training: Fine-tuned on around 800 hours of Portuguese speech - Task: Transcription (`task="transcribe"`) - Compute type: float16 (recommended) model = whisperx.loadmodel( "inesc-id/WhisperLv3-EP-X", device=device, computetype=computetype, language="pt", task="transcribe" )

This model is a fine-tuned Whisper variant of `openai/whisper-large-v3`, trained for Portuguese (pt) (European Portuguese, Brazilian and African and Asian Portuguese varieties) automatic speech recognition (ASR). From CAMÕES work. --- 🧠 Model Description - Base model: `openai/whisper-large-v3` - Architecture: Transformer encoder–decoder - Training: Fine-tuned on around 800 hours of Portuguese speech - Task: Transcription (`task="transcribe"`) - Compute type: float16 (recommended) model = whisperx.loadmodel( "inesc-id/WhisperLv3-X-PT-All", device=device, computetype=computetype, language="pt", task="transcribe" )

This model was trained with around 420h from CAMÕES work using a custom recipe in espnet. Model architecture and configuration is detailed in CAMÕES. Follow the ESPnet installation instructions if you haven't done that already. RESULTS Environments - date: `Mon Oct 13 13:39:24 WEST 2025`