Josh Meyer

https://github.com/coqui-ai/STT-examples/blob/32121db3660d128493e08464c77b60dca4c38cfd/mic_vad_streaming/mic_vad_streaming.py#L158

Feature Request: Upgrade to Coqui voice stack

3

👋 Hi there A lot has changed since my last PR was merged here. It's still an awesome project, but the quality of STT and TTS has greatly improved since...

How to add dictionary to Ossian?

1

Hi Oliver, I'm wondering how to add specific entries (like numbers or abbreviations) to something like a dictionary or lexicon for Ossian. I'm guessing it will look like this: ```...

Hi Oliver, When I do training on a 3.5 hour corpus, I run out of disk space (12Gigs) very fast: ``` OSSIAN$ du -h train/chv/speakers/news/naive_01_nn -d 1 26M train/chv/speakers/news/naive_01_nn/time_lab 888K...

Hi Oliver et al, I was looking up some things on `SKLDecisionTreePausePredictor`, because the `SKL` part wasn't obvious to me. Then I saw it's sci-kit learn, and that there's a...

Verify alphabet in pb* and tflite models

2

The alphabet files from Jaco models are inconsistent with the output of the models at runtime. It has been observed that the Jaco Spanish model can produce accented vowels, but...

Add local model

1

add a way to install a local model to the STT Model Manager from a checkpoint folder or from TFLite + Scorer files currently, you have to go through the...

Upgrade to 🐸STT v1.2.0

1

Hi there @solyarisoftware 👋 It would be a pretty easy lift to upgrade to 1.2.0, and the new English model is much better than the 0.9.3 model:)

Hi there 👋 This is a great resource, and it would be even better if updated to Coqui STT (the actively maintained fork of DeepSpeech). It should be a fairly...

Hi @AdroitAnandAI ! this is some impressive work, and it would be great to make it more usable by releasing model checkpoints as well... the current protobuf model files are...