Speech Recognition
6 pieces on Speech Recognition.
News & Analysis
MAI-Transcribe-2-Streaming Hits 2.5% WER in 0.13 Seconds
Microsoft’s streaming speech model ranks first of 38 systems for transcript accuracy, according to Artificial Analysis data reported by MarkTechPost.
Saaras V4 Covers All 22 Indian Languages With a 3B Hybrid Decoder
Sarvam AI's Saaras V4 handles all 22 scheduled Indian languages plus global English via a 3B hybrid state-space decoder, five output modes, and keyterm prompting at ₹30/hour.
Muse Voice Transcribe: 3.1% WER, One Model for ASR, Diarization, Endpointing
Meta Superintelligence Labs ships a single autoregressive model for streaming ASR, speaker diarization, and endpointing at $3.00 per 1,000 minutes.
Gemini 3.5 Transcribe: Choose Clean Text or Speaker Timing
Google documents a choice: SMART cleans speech, while VERBATIM supports speaker labels and word timing. Its launch included measured WER results.
Gemini 3.5 Transcribe Hits 2.6% WER, Cuts Latency 70% vs Chirp 3
Google's new speech-to-text model achieves 2.6% WER non-streaming and 4.0% streaming, with 70% faster time-to-final-transcription than Chirp 3.
ASR Benchmarks Are Gameable: 6 of 11 Top Models Reproduce Audio Errors
Hume AI tested 11 open-source ASR models and found six reproduce VoxPopuli's transcript errors even when audio contradicts them — exposing WER as a gameable metric.