chirp_2 Speech.Recognize is not as good as Speech.StreamingRecognize while trying out for Tamil language. Is there any workaround to make Recognize model work as good as streamingRecognize quality.
Hi @James23454454,
Welcome to the Google Cloud Community!
While you can’t directly improve the underlying chirp_2 Speech.Recognize model, here are ways to improve the performance of chirp_2 Speech.Recognize:
For more detailed information about chirp_2 Speech.recognize you may read this documentation.
Was this helpful? If so, please accept this answer as “Solution”. If you need additional assistance, reply here within 2 business days and I’ll be happy to help.
Speech.Recognize and Speech.StreamingRecognize theoretically should have same accuracy approximately or StreamingRecognize is actually better? Please assist
Also i will look into custom-models