Free release of ReazonSpeech, a completely made-in-Japan and extremely accurate speech recognition model for Japanese that can be used commercially
— Establishing a “new normal” in speech recognition —
Reazon Holdings, Inc. (Head office: Shinjuku-ku, Tokyo; Representative Director: Makoto Watanabe) has released ReazonSpeech, a Japanese speech recognition model boasting the world’s highest accuracy and the largest Japanese speech corpus in the world (19,000 hours)*.
Please see below for details.
https://prtimes.jp/main/html/rd/p/000000003.000102162.html
