OpenAI Releases Whisper: A New Open-Source Machine Learning Model For Multi-Lingual Automatic Speech Recognition

Using only an off-the-shelf transformer trained on 680,000 hours of weakly-supervised, multi-lingual audio data, OpenAI’s Whisper can approach human-level robustness and accuracy in ASR, all without the need for fine-tuning. Best of all, the model is open-source, with various weight sizes available to the public. The model As mentioned previously, the model is a standard […]

The post OpenAI Releases Whisper: A New Open-Source Machine Learning Model For Multi-Lingual Automatic Speech Recognition appeared first on MarkTechPost.

ai ethics ai shorts applications artificial intelligence automatic speech recognition country editors pick language model machine machine learning machine learning model openai releases speech speech recognition staff tech news technology unicorns usa whisper