#Speech-To-Text (2)

Waterfall Pagination

Microsoft MAI-Transcribe-2-Streaming tops Artificial Analysis: 2.5% WER with first partials ~100ms after speech — Japanese streamer demos it live: "the meeting-notes app era is over"

Microsoft MAI-Transcribe-2-Streaming tops Artificial Analysis: 2.5% WER with first partials ~100ms after speech — Japanese streamer demos it live: "the meeting-notes app era is over"

@studio_yebisu · 20 views · 2026-10-01

Speech-To-TextStreamingASR

Fish Audio upgrades its ASR model: speaker identification and inline emotion cues such as [laughter]

Fish Audio upgrades its ASR model: speaker identification and inline emotion cues such as [laughter]

@FishAudio · 423 views · 2026-09-28

ASRSpeech RecognitionEmotion Recognition