Tagged: automatic-speech-recognition

8 articles

Latest

Wav2Vec2 hits sub-5% WER with just 10 minutes of labeled speech

Fine-tune XLS-R 300M on 4 hours of Common Voice for multilingual speech recognition

Fine-Tune Whisper in 8 Hours to Conquer 96+ Languages

Meta's MMS slashes ASR error rates with 10-minute fine-tuning on 1,100 languages

ASR leaderboard scores are misleading — here's what actually matters when picking a model in 2026

Hugging Face locks down new speech datasets to stop AI benchmark gaming

NVIDIA's Conformer-LLM hybrid tops ASR accuracy, but open-source still trails in long-form audio

Wav2Vec2-BERT crushes Whisper on Mongolian ASR, 10x faster