Alok Prasad

Where can i get LapsBM1.4 dataset? link seems to be dead

microsoft sharepoint support for dvc remotes

45

It would be nice if the DVC also supports uploading of the model to sharepoint servers.

Issue: Missing initial frames causes deepspeech to skip first word, adding some silence about 5ms makes it work most of the time.

18

For support and discussions, please use our [Discourse forums](https://discourse.mozilla.org/c/deep-speech). If you've found a bug, or have a feature request, then please create an issue with the following information: - **Have...

functrace and funcgraph only supports single function

1

Currently, functrace and funcgraph only supports single function. There might be cases when we need to monitor multiple function in single tracing. I had to manually edit and multiple function...

fastspeech model to torch script convert for c++ inference

4

Any idea how to convert Fastspeech model to torch script and relevant c++ code for loading and inferencing from same to produce mel.pt file. in def synthesis i did ```...

How to check memory usage of on demand module loading

1

I am trying to load the module while system is up and then starting memstrack , but dont see any stats collected by it. i have tried both kmalloc and...

convert squeezewave model to pytorch script for C++ inference.

3

Any idea how to convert squeezewave model to pytorch script and relevant c++ code for loading and inferencing from same.

Running in CPU

6

Looks like Apex library needs CUDA, when i without cuda , getting below error. any idea. args.sampling_rate, args.is_fp16, args.denoiser_strength) File "inference.py", line 48, in main squeezewave, _ = amp.initialize(squeezewave, [],...