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! Just wondering if the KenLM is compatible with the Conformer model, and if so if there are any example scripts on how to include it? Thank you!
Hello! I'm wondering if is possible to use those models in real-time inference scenario like microphone stream. In other words, will models work good on smaller chunks of audio like...
Hello Team, I ran the librespeech contextnet experiment with success on a RTX 3080 and V100 with a batch size of 4 and 8 respectively. However, the same setup gives...
I tried to train the model with sentence_piece Tensorflow 2.3.2 and cuda 10.1 ``` python examples/deepspeech2/train.py --config config.yml --sentence_piece ``` But I got this error. ```INFO:tensorflow:Loading SentencePiece model ... INFO:tensorflow:Reading...
hi i trained the contextnet model for my custom datasets with mfcc featurizer and changing the required directories in config file and leaving the rest as it is. But after...
Hi, @usimarit In 'datasets/asr_dataset.py' line 141 u called line 41 of 'augmentations/augmentation.py', which is calling self.signal_augmentations = self.parse(config.pop("signal_augment", {})) self.feature_augmentations = self.parse(config.pop("feature_augment", {})) In config file no dict of signal_augment...
testing Jasper using subwords 
Facing this error while testing jasper.  env: 
It seems like deep context is an important piece for context biasing in end-to-end models, but I haven't found any open source implementation for it. Is there any plan to...
my OS : Ubuntu 18.04 my env : conda did I customized the code : No I did everything such as README file says. > conda create -y -n tfasr...
Metadata
Owner
Metadata
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords