From 8dab6d184a034ca86eafa644ea0d2100aadfe27d Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 09 五月 2023 10:58:33 +0800
Subject: [PATCH] Merge pull request #473 from alibaba-damo-academy/dev_smohan

---
 egs/alimeeting/sa-asr/conf/train_sa_asr_conformer.yaml |  115 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 115 insertions(+), 0 deletions(-)

diff --git a/egs/alimeeting/sa-asr/conf/train_sa_asr_conformer.yaml b/egs/alimeeting/sa-asr/conf/train_sa_asr_conformer.yaml
new file mode 100644
index 0000000..421d7df
--- /dev/null
+++ b/egs/alimeeting/sa-asr/conf/train_sa_asr_conformer.yaml
@@ -0,0 +1,115 @@
+# network architecture
+frontend: default
+frontend_conf:
+    n_fft: 400
+    win_length: 400
+    hop_length: 160
+
+# encoder related
+asr_encoder: conformer
+asr_encoder_conf:
+    output_size: 256    # dimension of attention
+    attention_heads: 4
+    linear_units: 2048  # the number of units of position-wise feed forward
+    num_blocks: 12      # the number of encoder blocks
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d # encoder architecture type
+    normalize_before: true
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    macaron_style: true
+    use_cnn_module: true
+    cnn_module_kernel: 15
+
+spk_encoder: resnet34_diar
+spk_encoder_conf:
+  use_head_conv: true
+  batchnorm_momentum: 0.5
+  use_head_maxpool: false
+  num_nodes_pooling_layer: 256
+  layers_in_block:
+    - 3
+    - 4
+    - 6
+    - 3
+  filters_in_block:
+    - 32
+    - 64
+    - 128
+    - 256
+  pooling_type: statistic
+  num_nodes_resnet1: 256
+  num_nodes_last_layer: 256
+  batchnorm_momentum: 0.5
+
+# decoder related
+decoder: sa_decoder
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    asr_num_blocks: 6
+    spk_num_blocks: 3
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.0
+    src_attention_dropout_rate: 0.0
+
+# hybrid CTC/attention
+model_conf:
+    spk_weight: 0.5
+    ctc_weight: 0.3
+    lsm_weight: 0.1     # label smoothing option
+    length_normalized_loss: false
+
+ctc_conf:
+    ignore_nan_grad: true
+
+# minibatch related
+batch_type: numel
+batch_bins: 10000000
+
+# optimization related
+accum_grad: 1
+grad_clip: 5
+max_epoch: 60
+val_scheduler_criterion:
+    - valid
+    - loss
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+-   - valid
+    - acc_spk
+    - max
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 10
+
+optim: adam
+optim_conf:
+   lr: 0.0005
+scheduler: warmuplr
+scheduler_conf:
+   warmup_steps: 8000
+
+specaug: specaug
+specaug_conf:
+    apply_time_warp: true
+    time_warp_window: 5
+    time_warp_mode: bicubic
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2
+

--
Gitblit v1.9.1