mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-09-18 13:34:20 +00:00
update RESULTS.md
This commit is contained in:
yaozengwei
parent
37e5689a08
commit
fef5e62ac4
@ -556,9 +556,9 @@ Number of model parameters 118129516 (i.e, 118.13 M).
|
||||
|
||||
| | test-clean | test-other | comment |
|
||||
|-------------------------------------|------------|------------|----------------------------------------|
|
||||
| greedy search (max sym per frame 1) | 2.39 | 5.57 | --epoch 39 --avg 7 --max-duration 600 |
|
||||
| modified beam search | 2.35 | 5.50 | --epoch 39 --avg 7 --max-duration 600 |
|
||||
| fast beam search | 2.38 | 5.50 | --epoch 39 --avg 7 --max-duration 600 |
|
||||
| greedy search (max sym per frame 1) | 2.43 | 5.72 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
| modified beam search | 2.43 | 5.69 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
| fast beam search | 2.43 | 5.67 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
|
||||
The training commands are:
|
||||
|
||||
@ -567,8 +567,8 @@ export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
||||
|
||||
./pruned_transducer_stateless5/train.py \
|
||||
--world-size 8 \
|
||||
--num-epochs 40 \
|
||||
--start-epoch 0 \
|
||||
--num-epochs 30 \
|
||||
--start-epoch 1 \
|
||||
--full-libri 1 \
|
||||
--exp-dir pruned_transducer_stateless5/exp-L \
|
||||
--max-duration 300 \
|
||||
@ -582,15 +582,15 @@ export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
||||
```
|
||||
|
||||
The tensorboard log can be found at
|
||||
<https://tensorboard.dev/experiment/Zq0h3KpnQ2igWbeR4U82Pw/>
|
||||
<https://tensorboard.dev/experiment/aWzDj5swSE2VmcOYgoe3vQ>
|
||||
|
||||
The decoding commands are:
|
||||
|
||||
```bash
|
||||
for method in greedy_search modified_beam_search fast_beam_search; do
|
||||
./pruned_transducer_stateless5/decode.py \
|
||||
--epoch 39 \
|
||||
--avg 7 \
|
||||
--epoch 30 \
|
||||
--avg 10 \
|
||||
--exp-dir ./pruned_transducer_stateless5/exp-L \
|
||||
--max-duration 600 \
|
||||
--decoding-method $method \
|
||||
@ -600,13 +600,14 @@ for method in greedy_search modified_beam_search fast_beam_search; do
|
||||
--nhead 8 \
|
||||
--encoder-dim 512 \
|
||||
--decoder-dim 512 \
|
||||
--joiner-dim 512
|
||||
--joiner-dim 512 \
|
||||
--use-averaged-model True
|
||||
done
|
||||
```
|
||||
|
||||
You can find a pretrained model, training logs, decoding logs, and decoding
|
||||
results at:
|
||||
<https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless5-2022-05-13>
|
||||
<https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless5-2022-07-07>
|
||||
|
||||
|
||||
#### Medium
|
||||
@ -615,9 +616,9 @@ Number of model parameters 30896748 (i.e, 30.9 M).
|
||||
|
||||
| | test-clean | test-other | comment |
|
||||
|-------------------------------------|------------|------------|-----------------------------------------|
|
||||
| greedy search (max sym per frame 1) | 2.88 | 6.69 | --epoch 39 --avg 17 --max-duration 600 |
|
||||
| modified beam search | 2.83 | 6.59 | --epoch 39 --avg 17 --max-duration 600 |
|
||||
| fast beam search | 2.83 | 6.61 | --epoch 39 --avg 17 --max-duration 600 |
|
||||
| greedy search (max sym per frame 1) | 2.87 | 6.92 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
| modified beam search | 2.83 | 6.75 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
| fast beam search | 2.81 | 6.76 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
|
||||
The training commands are:
|
||||
|
||||
@ -626,8 +627,8 @@ export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
||||
|
||||
./pruned_transducer_stateless5/train.py \
|
||||
--world-size 8 \
|
||||
--num-epochs 40 \
|
||||
--start-epoch 0 \
|
||||
--num-epochs 30 \
|
||||
--start-epoch 1 \
|
||||
--full-libri 1 \
|
||||
--exp-dir pruned_transducer_stateless5/exp-M \
|
||||
--max-duration 300 \
|
||||
@ -641,15 +642,15 @@ export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
||||
```
|
||||
|
||||
The tensorboard log can be found at
|
||||
<https://tensorboard.dev/experiment/bOQvULPsQ1iL7xpdI0VbXw/>
|
||||
<https://tensorboard.dev/experiment/04xtWUKPRmebSnpzN1GMHQ>
|
||||
|
||||
The decoding commands are:
|
||||
|
||||
```bash
|
||||
for method in greedy_search modified_beam_search fast_beam_search; do
|
||||
./pruned_transducer_stateless5/decode.py \
|
||||
--epoch 39 \
|
||||
--avg 17 \
|
||||
--epoch 30 \
|
||||
--avg 10 \
|
||||
--exp-dir ./pruned_transducer_stateless5/exp-M \
|
||||
--max-duration 600 \
|
||||
--decoding-method $method \
|
||||
@ -659,13 +660,14 @@ for method in greedy_search modified_beam_search fast_beam_search; do
|
||||
--nhead 4 \
|
||||
--encoder-dim 256 \
|
||||
--decoder-dim 512 \
|
||||
--joiner-dim 512
|
||||
--joiner-dim 512 \
|
||||
--use-averaged-model True
|
||||
done
|
||||
```
|
||||
|
||||
You can find a pretrained model, training logs, decoding logs, and decoding
|
||||
results at:
|
||||
<https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless5-M-2022-05-13>
|
||||
<https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless5-M-2022-07-07>
|
||||
|
||||
|
||||
#### Baseline-2
|
||||
@ -675,19 +677,19 @@ layers (24 v.s 12) but a narrower model (1536 feedforward dim and 384 encoder di
|
||||
|
||||
| | test-clean | test-other | comment |
|
||||
|-------------------------------------|------------|------------|-----------------------------------------|
|
||||
| greedy search (max sym per frame 1) | 2.41 | 5.70 | --epoch 31 --avg 17 --max-duration 600 |
|
||||
| modified beam search | 2.41 | 5.69 | --epoch 31 --avg 17 --max-duration 600 |
|
||||
| fast beam search | 2.41 | 5.69 | --epoch 31 --avg 17 --max-duration 600 |
|
||||
| greedy search (max sym per frame 1) | 2.54 | 5.72 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
| modified beam search | 2.47 | 5.71 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
| fast beam search | 2.5 | 5.72 | --epoch 30 --avg 10 --max-duration 600 |
|
||||
|
||||
```bash
|
||||
export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
||||
|
||||
./pruned_transducer_stateless5/train.py \
|
||||
--world-size 8 \
|
||||
--num-epochs 40 \
|
||||
--start-epoch 0 \
|
||||
--num-epochs 30 \
|
||||
--start-epoch 1 \
|
||||
--full-libri 1 \
|
||||
--exp-dir pruned_transducer_stateless5/exp \
|
||||
--exp-dir pruned_transducer_stateless5/exp-B \
|
||||
--max-duration 300 \
|
||||
--use-fp16 0 \
|
||||
--num-encoder-layers 24 \
|
||||
@ -699,18 +701,15 @@ export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
||||
```
|
||||
|
||||
The tensorboard log can be found at
|
||||
<https://tensorboard.dev/experiment/73oY9U1mQiq0tbbcovZplw/>
|
||||
|
||||
**Caution**: The training script is updated so that epochs are counted from 1
|
||||
after the training.
|
||||
<https://tensorboard.dev/experiment/foVHNyqiRi2LhybmRUOAyg>
|
||||
|
||||
The decoding commands are:
|
||||
|
||||
```bash
|
||||
for method in greedy_search modified_beam_search fast_beam_search; do
|
||||
./pruned_transducer_stateless5/decode.py \
|
||||
--epoch 31 \
|
||||
--avg 17 \
|
||||
--epoch 30 \
|
||||
--avg 10 \
|
||||
--exp-dir ./pruned_transducer_stateless5/exp-M \
|
||||
--max-duration 600 \
|
||||
--decoding-method $method \
|
||||
@ -720,13 +719,14 @@ for method in greedy_search modified_beam_search fast_beam_search; do
|
||||
--nhead 8 \
|
||||
--encoder-dim 384 \
|
||||
--decoder-dim 512 \
|
||||
--joiner-dim 512
|
||||
--joiner-dim 512 \
|
||||
--use-averaged-model True
|
||||
done
|
||||
```
|
||||
|
||||
You can find a pretrained model, training logs, decoding logs, and decoding
|
||||
results at:
|
||||
<https://huggingface.co/csukuangfj/icefall-asr-librispeech-pruned-transducer-stateless5-narrower-2022-05-13>
|
||||
<https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless5-B-2022-07-07>
|
||||
|
||||
|
||||
### LibriSpeech BPE training results (Pruned Stateless Transducer 4)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user