STT
STT copied to clipboard
🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
Can reference the PR from DeepSpeech: https://github.com/mozilla/DeepSpeech/pull/1848
Quality Voice Activity Detection as part of the API would be very handy. Real time STT in general can be processed these ways: -Continuous inference. -Push To Talk (PTT). -Voice...
An option to only allow sentences which occur in the language model would be very helpful. For example, the language model contains this: flap one gear down Currently STT can...
Once the .NET package on NuGet for Windows (Visual Studio) is available again, it would be nice to have a streaming VAD example project available.
right now, the docs only reference training on WAV files, but we can also train on opus. similarly, we should probably rename the expected column headers in the csv data...
OOM errors happen all the time in training for newcomers and pros... we should have a simple guide on using `--reverse_{train,test,dev}` and steps to choose the right batchsize on some...
Current behavior: If a flag is duplicated at the CLI and passed to `train.py`, there is no warning or error message, and the last setting is saved. This was first...
right now we use both `progressbar2` and `tqdm`, but the latter is better maintained and the former has caused issues. We should completely replace `progressbar2` with `tqdm`
- model zoo - STT-examples - model-manager - open-speech-corpora