nyadla-sys / whisper.tflite

Optimized OpenAI's Whisper TFLite Port for Efficient Offline Inference on Edge Devices
MIT License
159 stars 31 forks source link

Unable to transcribe recorded audio. #38

Open aaushsth opened 3 months ago

aaushsth commented 3 months ago

When i transcribe from asset folders wav file its working fine but not able to transcribe recorded audio. Its returning only "you" result. path -> path:/data/user/0/com.xxx.xxx.develop/files/MicInput.wav

vilassn commented 3 months ago

Wave file should have below format 16K sampling rate, mono channel, 16bits bit depth.

It can transcribe upto 30 seconds of audio data at a time.