At Microsoft Inspire 2023, Microsoft yesterday announced that OpenAI Whisper preview will be soon available via Azure OpenAI Service and Azure AI Speech.
The OpenAI Whisper model can offer transcription of human speech in 57 languages, and translation into English. It can also create transcripts with enhanced readability.
Azure OpenAI Service – OpenAI Whisper:
Through Azure OpenAI Service, developers will be able to run OpenAI Whisper model similar to the OpenAI Whisper API in features and functionality. Developers can use Whisper in Azure AI Studio when it becomes available.
Azure AI Speech – OpenAI Whisper:
Using Azure AI Speech Studio, developers will be able to try out OpenAI Whisper model. Azure AI Speech’s existing transcription model offers unique capabilities and advantages. So, customers must choose between OpenAI Whisper and Azure AI Speech’s existing model.
Within Azure AI Speech, developers can use the OpenAI Whisper model for batch transcription and also take advantage of existing features including async processing, speaker diarization, customization, and larger file sizes. Azure AI Speech improves Whisper transcription by enabling files up to 1GB in size and the ability to process large amounts of files by allowing you to batch up to 1000 files in a single request.
You can learn more about OpenAI Whisper model on Azure from the source link below.