Whisper NER Demo: https://huggingface.co/spaces/aiola/whisper ner v1 Peper: WhisperNER: Unified Open Named Entity and Speech Recognition . Code: https://github.com/aiola lab/whisper ner We introduce WhisperNER, a novel model that allows joint speech transcription and entity recognition. WhisperNER supports open type NER, enabling recognition of diverse and evolving entities at inference. The WhisperNER model is designed as a strong base model for the downstream task of ASR with NER, and can be fine tuned on specific datasets for improved performance. Training Details aiola/whisper ner v1 was trained on the NuNER dataset to perform joint audio transcription and NER tagging. The model was trained and evaluated only on English data. Check out the paper for full details. Usage Inference can be done using the following code (for inference code and more details check out the whisper ner repo).:
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy