luomingshuang commited on
Commit
4a6a58c
1 Parent(s): e7902ef

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Note: This recipe is trained with the codes from this PR https://github.com/k2-fsa/icefall/pull/233
2
+ And the SpecAugment codes from this PR https://github.com/lhotse-speech/lhotse/pull/604.
3
+
4
+ # Pre-trained Transducer-Stateless models for the TEDLium3 dataset with icefall.
5
+ The model was trained on full [TEDLium3](https://www.openslr.org/51) with the scripts in [icefall](https://github.com/k2-fsa/icefall).
6
+ ## Training procedure
7
+ The main repositories are list below, we will update the training and decoding scripts with the update of version.
8
+ k2: https://github.com/k2-fsa/k2
9
+ icefall: https://github.com/k2-fsa/icefall
10
+ lhotse: https://github.com/lhotse-speech/lhotse
11
+ * Install k2 and lhotse, k2 installation guide refers to https://k2.readthedocs.io/en/latest/installation/index.html, lhotse refers to https://lhotse.readthedocs.io/en/latest/getting-started.html#installation. I think the latest version would be ok. And please also install the requirements listed in icefall.
12
+ * Clone icefall(https://github.com/k2-fsa/icefall) and check to the commit showed above.
13
+ ```
14
+ git clone https://github.com/k2-fsa/icefall
15
+ cd icefall
16
+ ```
17
+ * Preparing data.
18
+ ```
19
+ cd egs/tedlium3/ASR
20
+ bash ./prepare.sh
21
+ ```
22
+ * Training
23
+ ```
24
+ export CUDA_VISIBLE_DEVICES="0,1,2,3"
25
+ ./transducer_stateless/train.py \
26
+ --world-size 4 \
27
+ --num-epochs 30 \
28
+ --start-epoch 0 \
29
+ --exp-dir transducer_stateless/exp \
30
+ --max-duration 200
31
+ ```
32
+ ## Evaluation results
33
+ The decoding results (WER%) on TEDLium3 (dev and test) are listed below, we got this result by averaging models from epoch 14 to 29.
34
+ The WERs are
35
+ | | dev | test | comment |
36
+ |------------------------------------|------------|------------|------------------------------------------|
37
+ | greedy search | 7.19 | 6.57 | --epoch 29, --avg 16, --max-duration 100 |
38
+ | beam search (beam size 4) | 7.12 | 6.37 | --epoch 29, --avg 16, --max-duration 100 |
39
+ | modified beam search (beam size 4) | 7.00 | 6.19 | --epoch 29, --avg 16, --max-duration 100 |