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
## Features - Another `text_featurizer` using wordpiece from [tensorflow_text.FastWordpieceTokenizer](https://www.tensorflow.org/text/api_docs/python/text/FastWordpieceTokenizer) - Update `SentencepieceFeaturizer` using [tensorflow_text.FastSentencepieceTokenizer](https://www.tensorflow.org/text/api_docs/python/text/FastSentencepieceTokenizer) - Add `tf_extract` function in `text_featurizer` to support dataset on TPUs with `use_tf: True` option -...
Hi, After one epoch, i got the following information: W tensorflow/core/kernels/data/cache_dataset_ops.cc:768] The calling iterator did not fully read the dataset being cached. In order to avoid unexpected truncation of the...
Hi, I started the training process and save some model in checkpoints. How can i use the most recent saved models and continue my training? If i start the training,...
Hi I'm trying to run the conformer notebook and getting an error. The only thing I've changed in that notebook is the location of the dataset and reducing epochs to...
Hello! I am pretty new to TensorFlow and have been tasked to deploy TensorFlowASR using Docker. In order to do that, I need the .pb file from the pretrained Conformer...
Hello everyone! After training, I save conformer model to SavedModel format by code below: ```python config = Config(config_path) speech_featurizer = TFSpeechFeaturizer(config.speech_config) text_featurizer = SubwordFeaturizer(config.decoder_config) conformer = Conformer(**config.model_config, vocabulary_size=text_featurizer.num_classes) conformer.make(speech_featurizer.shape) conformer.load_weights(model_path,...
Hello, I am trying to take this [pre-trained RNN-T model saved as h5](https://drive.google.com/drive/folders/1rYpiYF0F9JIsAKN2DCFFtEdfNzVbBLHe) and convert it to tflite. I have installed the required packages according to the requirements.txt, and have...
I have trained conformer model for the Librispeech config example. I would like to get audio - word piece alignment. to get output word pieces belongs to which parts of...
Hello, firstly, thank you for solving the beam issue. Now running the test.py with the trained model, the ETA time is huge. Its around 5 hours. Previously it got completed...
Metadata
Owner
Metadata
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords