Inference script to hear samples from AVSpeech Model ?

asteroid-team / asteroid

The PyTorch-based audio source separation toolkit for researchers

https://asteroid-team.github.io/

MIT License

2.21k stars 419 forks source link

Inference script to hear samples from AVSpeech Model ? #689

Open SutirthaChakraborty opened 7 months ago

SutirthaChakraborty commented 7 months ago

I have implemented the AVSpeech training and eval. How can hear out the sound and check how the model performs? Also, what is the ideal SNR for the model?

How can I find the code to infer to hear the outputs? The checkpoint is best.pth?