Josh Meyer

Coqui STT is well maintained, and upgrading would allow for better models and updates 💚 https://github.com/mozilla/DeepSpeech/issues/3693

@est31 -- if you're thinking to archive this project, you might include a link in the README to @tazz4843's new one: https://github.com/tazz4843/coqui-stt

this would be a super useful PR 😄 @nullpunktTUD Looks like you should add the pref test to `configs/complete.yaml` as well

Hi @kpu, I have this exact same question. I'm wondering if you have a more concrete idea on how this could be implemented. It would be a great feature for...

@kpu -- this can definitely be seen as a run-time domain adaptation, where the target-domain data is limited to small set of key-words, not sentences. It would be more than...

@reuben, I'm not sure what you mean by "prefix" tree. Are you suggesting making two trie structures (one only containing key words and one containing the original LM), and decoding...

This answer from #181 worked for me on Ubuntu 18.04: `markdown-pdf -p $(which phantomjs) mymarkdown.md`

https://www.kaggle.com/mfekadu/darpa-timit-acousticphonetic-continuous-speech

https://arxiv.org/abs/2009.10334

https://www.kaggle.com/shuyangli94/this-american-life-podcast-transcriptsalignments