alphacep / vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Apache License 2.0
7.38k stars 1.04k forks source link

vosk model audio recogniton issue #1448

Open utkarsh0509 opened 8 months ago

utkarsh0509 commented 8 months ago

I uploaded a 3 mins audio file and used the vosk-model-en-us-0.22 model to transcript it but got no transcript then i uploaded various recordings of different lengths some being 3 seconds and some 10 seconds , i spoke hello , transcript check etc but i am getting only this is output- audio_recordings/audio_drbXTsp.wav Get Transcript { "text" : "i" } audio_recordings/Audio_Introduction_0.3.mp3 Get Transcript { "text" : "though the" } audio_recordings/Audio_Introduction_0.17.mp3 Get Transcript { "text" : "three" } audio_recordings/Audio_Introduction_0.1.mp3 Get Transcript { "text" : "though the" } audio_recordings/audio_3U3K416.wav Get Transcript { "text" : "i" } audio_recordings/audio_eCu8sXt.wav Get Transcript { "text" : "i" }

get transcript is the button i created in my project to get a transcript of the recording