Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
| Date | Stars |
|---|---|
| 2026-07-24 | 2834 |
| 2026-07-25 | 2834 |
| 2026-07-28 | 2834 |
| 2026-07-30 | 2834 |
| 2026-07-31 | 2832 |
| 2026-08-06 | 2832 |
Today
— stars today
This week
-2 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Automatic-Speech-Recognition
End-to-end automatic speech recognition system implemented in TensorFlow.
## Recent Updates
- [x] **Support TensorFlow r1.0** (2017-02-24)
- [x] **Support dropout for dynamic rnn** (2017-03-11)
- [x] **Support running in shell file** (2017-03-11)
- [x] **Support evaluation every several training epoches automatically** (2017-03-11)
- [x] **Fix bugs for character-level automatic speech recognition** (2017-03-14)
- [x] **Improve some function apis for reusable** (2017-03-14)
- [x] **Add scaling for data preprocessing** (2017-03-15)
- [x] **Add reusable support for LibriSpeech training** (2017-03-15)
- [x] **Add simple n-gram model for random generation or statistical use** (2017-03-23)
- [x] **Improve some code for pre-processing and training** (2017-03-23)
- [x] **Replace TABs with blanks and add nist2wav converter script** (2017-04-20)
- [x] **Add some data preparation code** (2017-05-01)
- [x] **Add WSJ corpus standard preprocessing by s5 recipe** (2017-05-05)
- [x] **Restructuring of the project. Updated train.py for usage convinience** (2017-05-06)
- [x] **Finish feature module for timit, libri, wsj, support training for LibriSpeech** (2017-05-14)
- [x] **Remove some unnecessary codes** (2017-07-22)
- [x] **Add DeepSpeech2 implementation code** (2017-07-23)
- [x] **Fix some bugs** (2017-08-06)
- [x] **Add Layer Normalization RNN for efficiency** (2017-08-06)
- [x] **Add Madarian Speech Recognition support** (2017-08-06)
- [x] **Add Capsule Network Model** (2017-12-12)
- [x] **Release 1.0.0 version** (2017-12-14)
- [x] **Add Language Modeling Module** (2017-12-25)
- [x] **Will support TF1.12 soon** (2019-10-17)
## Recommendation
If you want to replace feed dict operation with Tensorflow multi-thread and fifoqueue input pipeline, you can refer to my repo [TensorFlow-Input-Pipeline](https://github.com/zzw922cn/TensorFlow-Input-Pipeline) for more example codes. My own practices prove that fifoqueue input pipeline would improve the training speed in some time.
If you want to look the history of speech recognition, I have collected the significant papers since 1981 in the ASR field. You can read awesome paper list in my repo [awesome-speech-recognition-papers](https://github.com/zzw922cn/awesome-speech-recognition-papers), all download links of papers are provided. I will update it every week to add new papers, including speech recognition, speech synthesis and language modelling. I hope that we won't miss any important papers in speech domain.
All my public repos will be updated in future, thanks for your stars!
## Install and Usage
Currently only python 3.5 is supported.
This project depends on scikit.audiolab, for which you need to have [libsndfile](http://www.mega-nerd.com/libsndfile/) installed in your system.
Clone the repository to your preferred directory and install using:
<pre>
sudo pip3 install -r requirements.txt
sudo python3 setup.py install
</pre>
To use, simply run the following command:
<pre>
python main/timit_train.py [-h] [--mode MODE] [--keep [KEEP]] [--nokeep]
[--level LEVEL] [--model MODEL] [--rnncell RNNCELL]
[--num_layer NUM_LAYER] [--activation ACTIVATION]
[--optimizer OPTIMIZER] [--batch_size BATCH_SIZE]
[--num_hidden NUM_HIDDEN] [--num_feature NUM_FEATURE]
[--num_classes NUM_CLASSES] [--num_epochs NUM_EPOCHS]
[--lr LR] [--dropout_prob DROPOUT_PROB]
[--grad_clip GRAD_CLIP] [--datadir DATADIR]
[--logdir LOGDIR]
optional arguments:
-h, --help show this help message and exit
--mode MODE set whether to train or test
--keep [KEEP] set whether to restore a model, when test mode, keep
should be set to True
--nokeep
--level LEVEL set the task level, phn, cha, or seq2seq, seq2seq will
be supported soon
--modExcerpt of 17,458 characters
Read on GitHub
140
wesinger · China
65
21
14
8
6
Aziz
2
1
Brian Cunnie · Majestic Labs ai · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:96cef3af721df827, topic:speech-recognition, name:speech recognition, desc:speech recognition
matched fp:96cef3af721df827, topic:deep-learning, topic:tensorflow
matched fp:96cef3af721df827, topic:evaluation