Downloads · 30 days
0
luomingshuang/icefall_asr_alimeeting_pruned_transducer_stateless2
icefall_asr_alimeeting_pruned_transducer_stateless2 is a machine learning model from luomingshuang. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Note: This recipe is trained with the codes from this PR https://github.com/k2-fsa/icefall/pull/378 And the SpecAugment codes from this PR https://github.com/lhotse-speech/lhotse/pull/604. The model was trained on the…
Downloads · 30 days
0
Access
Public
Updated Jul 19, 2022
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.pt1.1 GB · 97%
From the Hugging Face model README
Note: This recipe is trained with the codes from this PR https://github.com/k2-fsa/icefall/pull/378 And the SpecAugment codes from this PR https://github.com/lhotse-speech/lhotse/pull/604.
The model was trained on the far data of Alimeeting with the scripts in icefall based on the latest version k2.
The main repositories are list below, we will update the training and decoding scripts with the update of version.
k2: https://github.com/k2-fsa/k2
icefall: https://github.com/k2-fsa/icefall
lhotse: https://github.com/lhotse-speech/lhotse
git clone https://github.com/k2-fsa/icefall
cd icefall
cd egs/alimeeting/ASR
bash ./prepare.sh
export CUDA_VISIBLE_DEVICES="0,1,2,3"
./pruned_transducer_stateless2/train.py \
--world-size 4 \
--num-epochs 30 \
--start-epoch 0 \
--exp-dir pruned_transducer_stateless2/exp \
--lang-dir data/lang_char \
--max-duration 220
The decoding results (WER%) on Alimeeting(eval and test) are listed below, we got this result by averaging models from epoch 12 to 29. The WERs are
| eval | test | comment | |
|---|---|---|---|
| greedy search | 31.77 | 34.66 | --epoch 29, --avg 18, --max-duration 100 |
| modified beam search (beam size 4) | 30.38 | 33.02 | --epoch 29, --avg 18, --max-duration 100 |
| fast beam search (set as default) | 31.39 | 34.25 | --epoch 29, --avg 18, --max-duration 1500 |