Search results
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
Sep 21, 2022 · Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. We show that the use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language.
Robust Speech Recognition via Large-Scale Weak Supervision - Releases · openai/whisper.
Articles. Whispers of A.I.'s Modular Future - The future of machine learning lies in adaptable and accessible open-source speech-transcription programs. How to Run Whisper Speech Recognition Model - Explains how to install and run the model, as well as providing a performance analysis comparing Whisper to other models.
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
Constructs a Whisper processor which wraps a Whisper feature extractor and a Whisper tokenizer into a single processor. WhisperProcessor offers all the functionalities of WhisperFeatureExtractor and WhisperTokenizer .
Nov 17, 2023 · Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
Whisper large-v3 is supported in Hugging Face 🤗 Transformers. To run the model, first install the Transformers library through the GitHub repo. For this example, we'll also install 🤗 Datasets to load toy audio dataset from the Hugging Face Hub:
Use this model. Edit model card. Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.
