search

juliuskunze / speechless

Speech-to-text based on wav2letter built for transfer learning
https://arxiv.org/pdf/1706.00290.pdf
MIT License
96 stars 25 forks source link

No .wav file is generated #1

Closed saurabhvyas closed 7 years ago

saurabhvyas commented 7 years ago

I have downloaded english model and placed it in appropriate directory , I can see that model loads successfully , and audio input is working , but it never ends , it keeps detecting background sounds and still doesnt generate any .wav file , I have to manually press ctrl ^ c to stop it after few minutes .

juliuskunze commented 7 years ago

Hi! Please update to the new version. You can now customize noise thresholds and silence duration until termination, e. g. record_plot_and_save(Recorder(silence_threshold_for_unnormalized_audio=.1, silence_until_terminate_in_s=1))

saurabhvyas commented 7 years ago

Okay this issue has been fixed but still there is no text output produced , Also I only see .wav files generated and no spectrograms .

juliuskunze commented 7 years ago

Did you adjust the threshold to your mic? Did you call wav2letter.predict? Spectrogram should be in the same folder as generated .wav file.

saurabhvyas commented 7 years ago

image

Yes I did use predict method and , I saw in the folder there are 2 .wav files but no spectrogram

saurabhvyas commented 7 years ago

Also I did adjust parameters according to my mic , tried playing with them but no effect

saurabhvyas commented 7 years ago

Any update on this ?