mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-22 08:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add librispeech cr-ctc prefix beam search results

Browse Source
This commit is contained in:
pkufool 2024-10-29 16:03:32 +08:00
parent 154ef4cfa5
commit 676a8771b8
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
egs/librispeech/ASR/RESULTS.md
View File

@ -153,6 +153,7 @@ You can use <https://github.com/k2-fsa/sherpa> to deploy it.
| decoding method | test-clean | test-other | comment | | decoding method | test-clean | test-other | comment |
|--------------------------------------|------------|------------|---------------------| |--------------------------------------|------------|------------|---------------------|
| ctc-greedy-decoding | 2.57 | 5.95 | --epoch 50 --avg 25 | | ctc-greedy-decoding | 2.57 | 5.95 | --epoch 50 --avg 25 |
| ctc-prefix-beam-search | 2.52 | 5.85 | --epoch 50 --avg 25 |
The training command using 2 32G-V100 GPUs is: The training command using 2 32G-V100 GPUs is:
```bash ```bash
@ -184,7 +185,7 @@ export CUDA_VISIBLE_DEVICES="0,1"
The decoding command is: The decoding command is:
```bash ```bash
export CUDA_VISIBLE_DEVICES="0" export CUDA_VISIBLE_DEVICES="0"
for m in ctc-greedy-search; do for m in ctc-greedy-search ctc-prefix-beam-search; do
./zipformer/ctc_decode.py \ ./zipformer/ctc_decode.py \
--epoch 50 \ --epoch 50 \
--avg 25 \ --avg 25 \
@ -212,6 +213,7 @@ You can use <https://github.com/k2-fsa/sherpa> to deploy it.
| decoding method | test-clean | test-other | comment | | decoding method | test-clean | test-other | comment |
|--------------------------------------|------------|------------|---------------------| |--------------------------------------|------------|------------|---------------------|
| ctc-greedy-decoding | 2.12 | 4.62 | --epoch 50 --avg 24 | | ctc-greedy-decoding | 2.12 | 4.62 | --epoch 50 --avg 24 |
| ctc-prefix-beam-search | 2.1 | 4.61 | --epoch 50 --avg 24 |
The training command using 4 32G-V100 GPUs is: The training command using 4 32G-V100 GPUs is:
```bash ```bash
@ -238,7 +240,7 @@ export CUDA_VISIBLE_DEVICES="0,1,2,3"
The decoding command is: The decoding command is:
```bash ```bash
export CUDA_VISIBLE_DEVICES="0" export CUDA_VISIBLE_DEVICES="0"
for m in ctc-greedy-search; do for m in ctc-greedy-search ctc-prefix-beam-search; do
./zipformer/ctc_decode.py \ ./zipformer/ctc_decode.py \
--epoch 50 \ --epoch 50 \
--avg 24 \ --avg 24 \
@ -262,6 +264,7 @@ You can use <https://github.com/k2-fsa/sherpa> to deploy it.
| decoding method | test-clean | test-other | comment | | decoding method | test-clean | test-other | comment |
|--------------------------------------|------------|------------|---------------------| |--------------------------------------|------------|------------|---------------------|
| ctc-greedy-decoding | 2.03 | 4.37 | --epoch 50 --avg 26 | | ctc-greedy-decoding | 2.03 | 4.37 | --epoch 50 --avg 26 |
| ctc-prefix-beam-search | 2.02 | 4.35 | --epoch 50 --avg 26 |
The training command using 2 80G-A100 GPUs is: The training command using 2 80G-A100 GPUs is:
```bash ```bash
@ -292,7 +295,7 @@ export CUDA_VISIBLE_DEVICES="0,1"
The decoding command is: The decoding command is:
```bash ```bash
export CUDA_VISIBLE_DEVICES="0" export CUDA_VISIBLE_DEVICES="0"
for m in ctc-greedy-search; do for m in ctc-greedy-search ctc-prefix-beam-search; do
./zipformer/ctc_decode.py \ ./zipformer/ctc_decode.py \
--epoch 50 \ --epoch 50 \
--avg 26 \ --avg 26 \