Minor fixes.

This commit is contained in:
Fangjun Kuang 2022-02-19 22:26:11 +08:00
parent ecea4aac2f
commit 05de8e3b2e

View File

@ -9,7 +9,8 @@ You can find a pretrained model by visiting https://huggingface.co/shuanguanma/i
| beam search | 5.05|--epoch 59, --avg 10, --max-duration 100 |
You can use the following commands to reproduce our results:
```
```bash
export CUDA_VISIBLE_DEVICES="0,1,2,3"
python3 ./transducer_stateless/train.py \
--world-size 4 \
@ -30,6 +31,7 @@ You can use the following commands to reproduce our results:
--decoding-method greedy_search \
--context-size 2 \
--max-sym-per-frame 3
lang_dir=data/lang_char
dir=exp/transducer_stateless_context_size2
python3 ./transducer_stateless/decode.py \
@ -42,8 +44,6 @@ You can use the following commands to reproduce our results:
--max-sym-per-frame 3
```
### Aishell training results (Transducer-stateless)
#### 2022-02-18
(Pingfeng Luo) : The tensorboard log for training is available at <https://tensorboard.dev/experiment/SG1KV62hRzO5YZswwMQnoQ/>