Merge pull request #972 from Jackwaterveg/develop

update the ds2 online conf
pull/974/head
Hui Zhang 3 years ago committed by GitHub
commit 48709a99da
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -4,7 +4,7 @@
### Acoustic Model Released in paddle 2.X
Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech
:-------------:| :------------:| :-----: | -----: | :----------------- |:--------- | :---------- | :---------
[Ds2 Online Aishell Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s0/aishell.s0.ds_online.5rnn.debug.tar.gz) | Aishell Dataset | Char-based | 345 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.0824 |-| 151 h
[Ds2 Online Aishell Model](https://deepspeech.bj.bcebos.com/release2.2/aishell/s0/ds2_online_aishll_CER8.02_release.tar.gz) | Aishell Dataset | Char-based | 345 MB | 2 Conv + 5 LSTM layers with only forward direction | 0.080218 |-| 151 h
[Ds2 Offline Aishell Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s0/aishell.s0.ds2.offline.cer6p65.release.tar.gz)| Aishell Dataset | Char-based | 306 MB | 2 Conv + 3 bidirectional GRU layers| 0.065 |-| 151 h
[Conformer Online Aishell Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.chunk.release.tar.gz) | Aishell Dataset | Char-based | 283 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention + CTC | 0.0594 |-| 151 h
[Conformer Offline Aishell Model](https://deepspeech.bj.bcebos.com/release2.1/aishell/s1/aishell.release.tar.gz) | Aishell Dataset | Char-based | 284 MB | Encoder:Conformer, Decoder:Transformer, Decoding method: Attention | 0.0547 |-| 151 h

@ -46,10 +46,10 @@ model:
ctc_grad_norm_type: null
training:
n_epoch: 50
n_epoch: 65
accum_grad: 1
lr: 2e-3
lr_decay: 0.9 # 0.83
lr: 5e-4
lr_decay: 0.93
weight_decay: 1e-06
global_grad_clip: 3.0
log_interval: 100
@ -63,7 +63,7 @@ decoding:
decoding_method: ctc_beam_search
lang_model_path: data/lm/zh_giga.no_cna_cmn.prune01244.klm
alpha: 2.2 #1.9
beta: 5.0
beta: 4.3
beam_size: 300
cutoff_prob: 0.99
cutoff_top_n: 40

Loading…
Cancel
Save