TensorFlowASR
TensorFlowASR copied to clipboard
TensorSpeech
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords
Hi, I have a question on the predict network in the code. For example: Input training label is such as below. Now we got 261 vocabularies . (just for example,...
`TensorFlowASR` makes it quite easy to train and deploy almost SOTA ASR models, but it provides a pretrained model only in English. On the other hand, FAIR has recently published...
Hi, Thanks for developing this great tool kit. I had 2 questions about the conformer model :- 1. For the conformer model in ```examples/conformer``` , I think almost all the...
Hi, I also have a problem related to this ticket(https://github.com/TensorSpeech/TensorFlowASR/issues/44). I generated a CTC models with deepspeech2. I used a language model and voc download from http://www.openslr.org/11/. (3-gram.arpa is converted...
It could be fun to support training over multi-GPU. The goal is not to increase the batch size but to increase the model size, so the model would have to...
Hi, It is really great work. Thank you very much for the streaming transducers. Is it possible to add hints at runtime (In streaming transducers)(Section: 4) (Say I have some...
Is it possible to output token level timestep？ eg： hello 100-600 world 712-900 .......
What would be the best way to show/extract the confidence of the recognition (greedy or beam search) during inference. The sequence/word confidence would be interesting to see.
Hi, Self-supervised pretraining for speech representation is a promising technique for developing ASR in resource-constraint languages with little transcribed data, and SimCLR is applied with success for this purpose in...
Metadata
Owner
Metadata
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords