Annotate speech/TTS datasets with per-clip quality metrics (MOS, SNR, STOI, pitch, bandwidth, speaking rate, WER/CER, gender/emotion), multi-ASR consensus transcription and speaker labeling using the audiogear pipeline; then filter clips by quality and build listenable HTML QA reports. Use when asked to compute audio dataset metrics, build extended_metadata.csv, transcribe unlabeled audio, select clean TTS training data, or QA a speech dataset.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
lIkesimba9/audiogear142026년 7월 20일 업데이트