open-speech / speech-aligner

speech-aligner,是一个从“人声语音”及其“语言文本”,产生音素级别时间对齐标注的工具。speech-aligner, is a tool that generate phoneme-level alignment between human speech and its transcription
Other
392 stars 104 forks source link

怎么支持其他模型? #22

Open BarryKCL opened 1 year ago

BarryKCL commented 1 year ago

ERROR (speech-aligner[5.4.215~4-f2b7]:LogLikelihoodZeroBased():gmm/decodable-am-diag-gmm.cc:50) Dim mismatch: data dim = 48 vs. model dim = 39

特征怎么改成Deltas + Delta-Deltas形式? 3*13=39

BarryKCL commented 1 year ago

不需要ComputeKaldiPitch就行了