harisbinzia/pronouncur

PronouncUR: An Urdu Pronunciation Lexicon Generator

pronouncur's Issues

Usage guide

Hi,
This seems to be amazing but unfortunately there is no usage guide in the readme. It would be great if you can tell us how to use it and what options are in the application.

AttributeError: module 'tensorflow.contrib.rnn' has no attribute 'core_rnn_cell'

On running app.py with python3 I received AttributeError: module 'tensorflow.contrib.rnn' has no attribute 'core_rnn_cell'

The whole output is as follows:

(tf1) metanet@metanet-Precision-Tower-7810:~/ProgramFiles/pronouncUR/PronouncUR$ python3 app.py
Loading vocabularies from itudict
WARNING:tensorflow:From /home/metanet/ProgramFiles/pronouncUR/PronouncUR/g2p.py:66: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.

2022-07-03 11:01:30.365847: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
2022-07-03 11:01:30.406687: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: NVIDIA GeForce RTX 3080 Ti major: 8 minor: 6 memoryClockRate(GHz): 1.665
pciBusID: 0000:03:00.0
2022-07-03 11:01:30.407012: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2022-07-03 11:01:30.408631: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2022-07-03 11:01:30.410073: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2022-07-03 11:01:30.410381: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2022-07-03 11:01:30.412172: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2022-07-03 11:01:30.413463: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2022-07-03 11:01:30.417611: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2022-07-03 11:01:30.417960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2022-07-03 11:01:30.418399: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2022-07-03 11:01:30.446934: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2394455000 Hz
2022-07-03 11:01:30.451648: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55f574bdb5c0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2022-07-03 11:01:30.451699: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2022-07-03 11:01:30.699749: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55f576b8e680 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2022-07-03 11:01:30.699826: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce RTX 3080 Ti, Compute Capability 8.6
2022-07-03 11:01:30.700408: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: NVIDIA GeForce RTX 3080 Ti major: 8 minor: 6 memoryClockRate(GHz): 1.665
pciBusID: 0000:03:00.0
2022-07-03 11:01:30.700510: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2022-07-03 11:01:30.700545: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2022-07-03 11:01:30.700576: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2022-07-03 11:01:30.700610: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2022-07-03 11:01:30.700642: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2022-07-03 11:01:30.700674: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2022-07-03 11:01:30.700707: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2022-07-03 11:01:30.701298: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2022-07-03 11:01:30.701377: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2022-07-03 11:01:30.701951: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2022-07-03 11:01:30.701986: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0
2022-07-03 11:01:30.702006: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N
2022-07-03 11:01:30.702727: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 11050 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 3080 Ti, pci bus id: 0000:03:00.0, compute capability: 8.6)
Creating 2 layers of 512 units.
WARNING:tensorflow:

WARNING:tensorflow:
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
• https://github.com/tensorflow/io (for I/O related ops)
  If you depend on functionality not listed there, please file an issue.

Traceback (most recent call last):
File "app.py", line 23, in
g2p_model.load_decode_model()
File "/home/metanet/ProgramFiles/pronouncUR/PronouncUR/g2p.py", line 74, in load_decode_model
forward_only=True)
File "/home/metanet/ProgramFiles/pronouncUR/PronouncUR/seq2seq_model.py", line 121, in init
single_cell = tf.contrib.rnn.core_rnn_cell.GRUCell(size)
AttributeError: module 'tensorflow.contrib.rnn' has no attribute 'core_rnn_cell'

(tf1) metanet@metanet-Precision-Tower-7810:~/ProgramFiles/pronouncUR/PronouncUR$ pip show tensorflow
Name: tensorflow
Version: 1.15.0
Summary: TensorFlow is an open source machine learning framework for everyone.
Home-page: https://www.tensorflow.org/
Author: Google Inc.
Author-email: [email protected]
License: Apache 2.0
Location: /home/metanet/miniconda3/envs/tf1/lib/python3.7/site-packages
Requires: numpy, protobuf, absl-py, wrapt, tensorflow-estimator, opt-einsum, termcolor, keras-applications, grpcio, google-pasta, six, gast, tensorboard, keras-preprocessing, astor, wheel
Required-by:

(tf1) metanet@metanet-Precision-Tower-7810:~/ProgramFiles/pronouncUR/PronouncUR$

Open source dataset

Would you please open source your dataset so as to move the research in this area forward? It would be much appreciated. One of the bottlenecks in the research in the Urdu language is the scarcity of the available dataset.