Microsoft has improved the quality of the transcripts generated by Azure Media Indexer, along with expanding local support so as to eventually accomplish their goal of being able to recognize all human speech on the
Azure cloud.
The company is now all set to make the release of the improvements to Azure Media Indexer 2 Preview: Per the
official blog, they are stated below:
- Japanese language models for public (preview) consumption in Azure Media Indexer 2
- Removal of the 10 minute processing limit
- Additional quality improvements with respect to punctuation and grammar
The Japanese language work sin an identical manner to all the other language models, simply provide the language code in the configuration file.