English text: The girls stared at their father. Mrs. Bennet said only, "Nonsense, nonsense!"

remove ! then the error disappeared.

Error Log:

Traceback (most recent call last):
File "readText_Paddle.py", line 1175, in
englishTxt2WavbyPaddle(mp3filepath,textforSpeak)
File "readText_Paddle.py", line 147, in englishTxt2WavbyPaddle
wav_file = tts_executor(
File "

As implemented in Python in

alphacep/vosk-api@5e46825

1. Recorder.SampleData()
(1) 命名建议：这个方法的功能相当于是重采样，而且本质上只会降低采样率，建议改名为ResampleData/DownsampleData更合适。
(2) 现在的的降低采样率实现方式只是按比例舍弃采样（decimation），但是从信号处理的角度，单纯这样做的话会有aliasing effect（混叠），引起严重失真（注意，此现象并非由于采样点减少本身导致的音质变差）。标准的降低采样率方式应当在处理之前加入低通滤波过程。如采样比非整数，则应先提高采样率再降低采样率。参见https://zh.wikipedia.org/zh-my/%E9%99%8D%E9%87%87%E6%A0%B7

2. pcmAbsSum
目前音量显示用信号绝对值之和的平均值，此方法据我所知并非标准做法，而且不反映能量/功率（power）。常

Creating CSV files manually is a lot of work. This could be automated by a script if the name of the WAV file is the same as the transcript.

The same could be done for creating a language model input text file. A script could pull the transcript from the WAV file name.

Design a logo for LibreASR and share it here.

To make an open source project cool, it should have a logo 😄

For simplified Vosk processing like

https://github.com/Aculeasis/vosk-rest

❓ Questions & Help

Details

Each call of the error rate accumulates the distance and length. Why is that?Is it to have a running average kind of thing?
Why don't you just return the point-wise wer? @upskyy