tensor2tensor
tensor2tensor copied to clipboard
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
### Description I have been trying to create a model for automatic speech recognition training on this [dataset](https://www.tarteel.io/dataset). I tried following this tutorial [ASR With Transformer](https://colab.research.google.com/github/tensorflow/tensor2tensor/blob/master/tensor2tensor/notebooks/asr_transformer.ipynb#scrollTo=Qz5u2O5LvShm) and got it done...
### Description Hi, Can you please share an example code to convert speech to text using Tensor2Tensor (maybe with transformer) mode? This will help a lot. Thanks Nagaraju ... ###...
Dear experts, I want to use Tensor2Tensor for image classification tasks. After model training, I got its CKPT and MATA files. Since I don’t know the specific structure of the...
Thank you very much.
### Description If I have another model, but in sub-layer of my model, I want to add a transformer-encoder layer and add a tranformer-decoder or multi transformer-decoder in another layer....
### Description when use HPARAMS=universal_transformer_base_fp16 or HPARAMS=transformer_fairseq_fp16_activation_big , tensor2tensor not work /home/username/.pyenv/versions/3.7.0/lib/python3.7/site-packages/tensor2tensor/utils/t2t_model.py:325 call * sharded_logits, losses = self.model_fn_sharded(sharded_features) /home/username/.pyenv/versions/3.7.0/lib/python3.7/site-packages/tensor2tensor/utils/t2t_model.py:402 model_fn_sharded * sharded_logits, sharded_losses = dp(self.model_fn, datashard_to_features) /home/username/.pyenv/versions/3.7.0/lib/python3.7/site-packages/tensor2tensor/utils/expert_utils.py:231 __call__ * outputs.append(fns[i](*my_args[i],...
Serving locally using tensorflow_model_server works fine. I've put an exported model/version on Google Cloud ML Engine. The question is how do I set the query.py to use a remote server...
Hi, users are unable to run Tensor2tensor due to dependency conflict with _**cloudpickle**_ package. As shown in the following full dependency graph of Tensor2tensor, gym requires _** cloudpickle~=1.2.0**_,while tensorflow-probability requires...
# TIMIT dataset - `audio_timit_characters_test` - speech recognition For the TIMIT data set, how to solve the `audio_compression` error in training? ``` File "/home/yongqiang/miniconda3/envs/tf_cpu_1.4.1_py2/lib/python2.7/site-packages/tensor2tensor/models/modalities.py", line 316, in bottom for i...
layers/common_hparams.py mentions a hyperparameter "pretrained_model_dir": "Directory containing a checkpoint for a pretrained model. This will only be used if a new run is being started. Parameters not found in the...