What I really like in speech recognition and what keeps me excited about it is an active on-going development of speech recognition technology which boosts both speech recognition results and,...
While dataset sizes grow beyond 10 thousand hours (Gigaspeech) the compute requirements for speech recognition research also grow. Any research even a simple architecture testing gets harder and harder because...
Not long after Citrinet Nvidia NeMo released Conformer-CTC model. As usual, forget about Citrinet now, Conformer-CTC is way better. The model is available for download [here](https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_conformer_ctc_large), latest Nemo repo supports...
This week ICASSP 2021 starts online. A bit late time for a year and everyone already looked on the publications. Many papers are already on Arxiv for some time, some...
The race for biggest model continue. Recently NVIDIA came out with a Citrinet model, a bigger and more advanced version of Quartznet. The publication is: [Citrinet: Closing the Gap between...
With the development of neural network toolkits it seems that the technology reached the point where huge network can remember and recognize almost everything as long as it was properly...
We continue testing of the most advanced ASR models, here we try famous Wav2Vec2.0, an impressive work by Facebook. Here are previous posts: Nvidia Nemo Wav2Letter RASR The ideas behind...
In Russian community Nvidia NEMO got some popularity recently. Big companies like VK.COM and Yandex announce they use Nemo for their production systems. Quartznet and Jasper architectures mentioned here and...
There are so many toolkits and model releases that some interesting things left unnoticed. Some time ago Facebook published a small paper Rethinking Evaluation in ASR: Are Our Models Robust...
Espnet toolkit has got some great recent developments as described in Recent Developments on ESPnet Toolkit Boosted by Conformer Results include great accuracy numbers, so I tried Espnet recently on...