zamia-speech

Yes, there are really good open source speech to text tools (automatic speech recognition (ASR) is the common name for that). Kaldi (https://kaldi-asr.org/) is probably the most well known, and supports hybrid NN-HMM and lattice-free MMI models. Kaldi is used by many people both in research and in production. Lingvo (https://github.com/tensorflow/lingvo) is the open source version of Google speech recognition toolkit, with support mostly for end-to-end models. ESPNet (https://github.com/espnet/espnet) is good and well known for end-to-end models as well. RASR (https://github.com/rwth-i6/rasr) + RETURNN (https://github.com/rwth-i6/returnn) are very good as well, both for end-to-end models and hybrid NN-HMM, but they are for non-commercial applications only (or you need a commercial licence) (disclaimer: I work at the university chair which

Heres a Project which is usable for speech to text via API and docker image: https://github.com/gooofy/zamia-speech#download https://github.com/mpuels/docker-py-kaldi-asr-and-model (also supporting german language pretty good but not production ready)

I'll second the recommendation for Kaldi. It's more complicated to get running vs pocketsphinx, but in my experience Kaldi has better accuracy/lower latency in general cases vs pocketsphinx (assuming caveats below). https://github.com/gooofy/zamia-speech/ has been training good [acoustic] models which are worth looking at (including training with robustness against noise). They've also got lots of code and docker images and documentation. pocketsphinx isn't actually that bad to use with their latest acoustic models and small vocabularies (so its utility depends on your exact use case). But it's not generally good with far field mics/dsp processed audio, not really good with noise, and in my experiments quite not as fast as Kaldi. Better/larger language models in my experience make a world of difference (esp in the general vocab case) for

Could you explain, what's the difference to - https://github.com/gooofy/zamia-speech#asr-models - https://github.com/mpuels/docker-py-kaldi-asr-and-model in regards of speech recognition except the fact that its easier to use?

The Kaldi models come from Zamia (https://github.com/gooofy/zamia-speech) and their accuracy is quite high. They're a bit slow on a Pi, though there are some performance improvements coming soon. Rhasspy is designed to recognize user-specified voice commands, so the accuracy will highly depend on the complexity of your commands. If needed, you can also try doing open transcription: https://rhasspy.readthedocs.io/en/latest/speech-to-text/#ope...

Thanks! In tests with a high quality headset mic, I've been able to get up to 98% (intent) recognition accuracy. Keep in mind that this is for a closed domain with only ~600k possible sentences. I'd expect performance degradation with a free-standing mic like the PS3 eye, but I don't have any measurements yet. Because Rhasspy combines both a speech and intent recognizer, transcription word error rate isn't as important if the correct intent/named entities can still be recognized. When your intents have more distinct vocabularies, your recognition rate will be higher. I've had folks with British and Australian accents use Rhasspy successfully (with the CMU English 5.2 acoustic model). Some recent tests with an nnet3 Kaldi model have produced better results (https://github.com/gooofy/zamia-speech), especially with noise. I plan to add this

Well, for the speech detection part, I think, there are some projects that look promising. I recently found https://github.com/gooofy/zamia-speech, which works for english and german. German is pretty bad atm, but english should work fine. Nice part: You only have to spin up a docker container and a python script and can perform offline speech to text :-) Microphone input is also supported.