Merge pull request #1610 from PaddlePaddle/Jackwaterveg-patch-1-1

[Doc] Update chunk conformer model info.md

docs/source/released_model.md

@@ -8,7 +8,8 @@ Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER |
 :-------------:| :------------:| :-----: | -----: | :-----: |:-----:| :-----:  | :-----:  | :-----: 
 [Ds2 Online Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_online_aishell_ckpt_0.1.1.model.tar.gz) | Aishell Dataset | Char-based | 345 MB  | 2 Conv + 5 LSTM layers with only forward direction | 0.080 |-| 151 h | [D2 Online Aishell ASR0](../../examples/aishell/asr0) 
 [Ds2 Offline Aishell ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr0/asr0_deepspeech2_aishell_ckpt_0.1.1.model.tar.gz)| Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers| 0.064 |-| 151 h | [Ds2 Offline Aishell ASR0](../../examples/aishell/asr0) 
-[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 | 177 MB  | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0483 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) 
+[Conformer Online Aishell ASR1 Model](https://paddlespeech.bj.bcebos.com/s2t/aishell/asr1/asr1_chunk_conformer_aishell_ckpt_0.1.2.model.tar.gz) | Aishell Dataset | Char-based | 189 MB  | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention rescoring | 0.0565 |-| 151 h | [Conformer Online Aishell ASR1](../../examples/aishell/asr1) 
+[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 | 0.0483 |-| 151 h | [Conformer Offline Aishell ASR1](../../examples/aishell/asr1) 
 [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) 
 [Ds2 Offline Librispeech ASR0 Model](https://paddlespeech.bj.bcebos.com/s2t/librispeech/asr0/asr0_deepspeech2_librispeech_ckpt_0.1.1.model.tar.gz)| Librispeech Dataset | Char-based | 518 MB | 2 Conv + 3 bidirectional LSTM layers| - |0.0725| 960 h | [Ds2 Offline Librispeech ASR0](../../examples/librispeech/asr0) 
 [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 |-| 0.0337 | 960 h | [Conformer Librispeech ASR1](../../examples/librispeech/asr1) 

examples/aishell/asr1/RESULTS.md

@@ -12,14 +12,16 @@ paddlespeech version: 0.1.2
 
 
 ## Chunk Conformer
+paddle version: 2.2.2  
+paddlespeech version: 0.1.2  
 Need set `decoding.decoding_chunk_size=16` when decoding.
 
 | Model | Params | Config | Augmentation| Test set | Decode method | Chunk Size & Left Chunks | Loss | CER |  
 | --- | --- | --- | --- | --- | --- | --- | --- | --- |  
-| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug + shift | test | attention | 16, -1 | - | 0.061939 |  
-| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug + shift | test | ctc_greedy_search | 16, -1 | - | 0.070806 |  
-| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug + shift | test | ctc_prefix_beam_search | 16, -1 | - | 0.070739 |  
-| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug + shift | test | attention_rescoring | 16, -1 |  - | 0.059400 |  
+| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug | test | attention | 16, -1 | - | 0.0573884 |  
+| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug | test | ctc_greedy_search | 16, -1 | - | 0.06599091 |  
+| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug | test | ctc_prefix_beam_search | 16, -1 | - | 0.065991 |  
+| conformer | 47.06M | conf/chunk_conformer.yaml | spec_aug | test | attention_rescoring | 16, -1 |  - | 0.056502 |  
 
 
 ## Transformer 

examples/aishell/asr1/conf/chunk_conformer.yaml

@@ -39,6 +39,7 @@ model_conf:
     ctc_weight: 0.3
     lsm_weight: 0.1     # label smoothing option
     length_normalized_loss: false
+    init_type: 'kaiming_uniform' 
 
 ###########################################
 #                   Data                  #
@@ -61,12 +62,12 @@ feat_dim: 80
 stride_ms: 10.0
 window_ms: 25.0
 sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs 
-batch_size: 64
+batch_size: 32
 maxlen_in: 512  # if input length  > maxlen-in, batchsize is automatically reduced
 maxlen_out: 150  # if output length > maxlen-out, batchsize is automatically reduced
 minibatches: 0 # for debug
 batch_count: auto
-batch_bins: 0 
+batch_bins: 0
 batch_frames_in: 0
 batch_frames_out: 0
 batch_frames_inout: 0
@@ -77,13 +78,13 @@ num_encs: 1
 ###########################################
 #                 Training                #
 ###########################################
-n_epoch: 240 
-accum_grad: 2
+n_epoch: 180 
+accum_grad: 1
 global_grad_clip: 5.0
 dist_sampler: True
 optim: adam
 optim_conf:
-  lr: 0.002
+  lr: 0.001
   weight_decay: 1.0e-6
 scheduler: warmuplr
 scheduler_conf:
@@ -93,4 +94,3 @@ log_interval: 100
 checkpoint:
   kbest_n: 50
   latest_n: 5
-