Skip to content

D
DeepSpeech

PaddlePaddle / DeepSpeech
大约 2 年 前同步成功

通知 210
Star 8425
Fork 1598
D
DeepSpeech
未验证 提交 66c59296 编写于 作者: 小湉湉's avatar 小湉湉 提交者： GitHub
浏览文件
操作

Merge pull request #2104 from PaddlePaddle/Jackwaterveg-patch-1 

[Doc] Update conformer_aishell pretrained model
上级 a0d1888c 32e8c6f1
隐藏空白更改
内联 并排
Showing with 9 addition and 9 deletion
docs/source/released_model.md
浏览文件 @ 66c59296
...@@ -10,7 +10,7 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | ...@@ -10,7 +10,7 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER |
[Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_offline_aishell_ckpt_1.0.1.model.tar.gz)| Aishell Dataset | Char-based | 1.4 GB | 2 Conv + 5 bidirectional LSTM layers| 0.0554 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) | inference/python | [Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_offline_aishell_ckpt_1.0.1.model.tar.gz)| Aishell Dataset | Char-based | 1.4 GB | 2 Conv + 5 bidirectional LSTM layers| 0.0554 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) | inference/python |
[Conformer Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz) | WenetSpeech Dataset | Char-based | 457 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.11 (test\_net) 0.1879 (test\_meeting) |-| 10000 h |- | python | [Conformer Online Wenetspeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/wenetspeech/asr1/asr1_chunk_conformer_wenetspeech_ckpt_1.0.0a.model.tar.gz) | WenetSpeech Dataset | Char-based | 457 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.11 (test\_net) 0.1879 (test\_meeting) |-| 10000 h |- | python |
[Conformer Online Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_chunk_conformer_aishell_ckpt_0.2.0.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.0544 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1) | python | [Conformer Online Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_chunk_conformer_aishell_ckpt_0.2.0.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring| 0.0544 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1) | python |
[Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_0.1.2.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0464 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) | python | [Conformer Offline Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_conformer_aishell_ckpt_1.0.1.model.tar.gz) | Aishell Dataset | Char-based | 189 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0460 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) | python |
[Transformer Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_transformer_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 128 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0523 || 151 h | [Transformer Aishell ASR1](../../examples/aishell/asr1) | python | [Transformer Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_transformer_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 128 MB | Encoder:Transformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0523 || 151 h | [Transformer Aishell ASR1](../../examples/aishell/asr1) | python |
[Ds2 Offline Librispeech ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr0/asr0_deepspeech2_offline_librispeech_ckpt_1.0.1.model.tar.gz)| Librispeech Dataset | Char-based | 1.3 GB | 2 Conv + 5 bidirectional LSTM layers| - |0.0467| 960 h | [Ds2 Offline Librispeech ASR0](../../examples/librispeech/asr0) | inference/python | [Ds2 Offline Librispeech ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr0/asr0_deepspeech2_offline_librispeech_ckpt_1.0.1.model.tar.gz)| Librispeech Dataset | Char-based | 1.3 GB | 2 Conv + 5 bidirectional LSTM layers| - |0.0467| 960 h | [Ds2 Offline Librispeech ASR0](../../examples/librispeech/asr0) | inference/python |
[Conformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/asr1_conformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 191 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0338 | 960 h | [Conformer Librispeech ASR1](../../examples/librispeech/asr1) | python | [Conformer Librispeech ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr1/asr1_conformer_librispeech_ckpt_0.1.1.model.tar.gz) | Librispeech Dataset | subword-based | 191 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring |-| 0.0338 | 960 h | [Conformer Librispeech ASR1](../../examples/librispeech/asr1) | python |
......
examples/aishell/asr1/RESULTS.md
浏览文件 @ 66c59296
...@@ -2,13 +2,13 @@ ...@@ -2,13 +2,13 @@
## Conformer ## Conformer
paddle version: 2.2.2 paddle version: 2.2.2
paddlespeech version: 0.2.0 paddlespeech version: 1.0.1
| Model | Params | Config | Augmentation| Test set | Decode method | Loss | CER | | Model | Params | Config | Augmentation| Test set | Decode method | Loss | CER |
| --- | --- | --- | --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- | --- | --- | --- |
| conformer | 47.07M | conf/conformer.yaml | spec_aug | test | attention | - | 0.0530 | | conformer | 47.07M | conf/conformer.yaml | spec_aug | test | attention | - | 0.0522 |
| conformer | 47.07M | conf/conformer.yaml | spec_aug | test | ctc_greedy_search | - | 0.0495 | | conformer | 47.07M | conf/conformer.yaml | spec_aug | test | ctc_greedy_search | - | 0.0481 |
| conformer | 47.07M | conf/conformer.yaml | spec_aug| test | ctc_prefix_beam_search | - | 0.0494 | | conformer | 47.07M | conf/conformer.yaml | spec_aug| test | ctc_prefix_beam_search | - | 0.0480 |
| conformer | 47.07M | conf/conformer.yaml | spec_aug | test | attention_rescoring | - | 0.0464 | | conformer | 47.07M | conf/conformer.yaml | spec_aug | test | attention_rescoring | - | 0.0460 |
## Conformer Streaming ## Conformer Streaming
......
examples/aishell/asr1/conf/conformer.yaml
浏览文件 @ 66c59296
...@@ -57,7 +57,7 @@ feat_dim: 80 ...@@ -57,7 +57,7 @@ feat_dim: 80
stride_ms: 10.0 stride_ms: 10.0
window_ms: 25.0 window_ms: 25.0
sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs
batch_size: 64 batch_size: 32
maxlen_in: 512 # if input length > maxlen-in, batchsize is automatically reduced maxlen_in: 512 # if input length > maxlen-in, batchsize is automatically reduced
maxlen_out: 150 # if output length > maxlen-out, batchsize is automatically reduced maxlen_out: 150 # if output length > maxlen-out, batchsize is automatically reduced
minibatches: 0 # for debug minibatches: 0 # for debug
...@@ -73,8 +73,8 @@ num_encs: 1 ...@@ -73,8 +73,8 @@ num_encs: 1
########################################### ###########################################
# Training # # Training #
########################################### ###########################################
n_epoch: 240 n_epoch: 150
accum_grad: 2 accum_grad: 8
global_grad_clip: 5.0 global_grad_clip: 5.0
dist_sampler: True dist_sampler: True
optim: adam optim: adam
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或