streaming st

egs2/fisher_callhome_spanish/st1/conf/decode_streaming_st.yaml

@@ -0,0 +1,5 @@
+batch_size: 1
+beam_size: 10
+nbest: 1
+lm_weight: 0.0
+sim_chunk_length: 5120

egs2/fisher_callhome_spanish/st1/conf/train_st_streaming.yaml

@@ -0,0 +1,95 @@
+# network architecture
+
+# frontend related
+frontend: default
+frontend_conf:
+    n_fft: 512
+    win_length: 400
+    hop_length: 160
+
+# encoder related
+# encoder related
+encoder: contextual_block_transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    normalize_before: true
+    block_size: 40
+    hop_size: 16
+    look_ahead: 16
+    init_average: true
+    ctx_pos_enc: true
+
+# decoder related
+decoder: transformer
+decoder_conf:
+    input_layer: embed
+    num_blocks: 6
+    linear_units: 2048
+    dropout_rate: 0.1
+
+extra_asr_decoder: transformer
+extra_asr_decoder_conf:
+    input_layer: embed
+    num_blocks: 2
+    linear_units: 2048
+    dropout_rate: 0.1
+
+extra_mt_decoder: transformer
+extra_mt_decoder_conf:
+    input_layer: embed
+    num_blocks: 2
+    linear_units: 2048
+    dropout_rate: 0.1
+
+# loss related
+model_conf:
+    asr_weight: 0.3
+    mt_weight: 0.0
+    mtlalpha: 1.0
+    lsm_weight: 0.1
+    length_normalized_loss: false
+
+# optimization related
+optim: adam
+accum_grad: 1
+grad_clip: 3
+max_epoch: 50
+optim_conf:
+    lr: 2.5
+scheduler: noamlr
+scheduler_conf:
+    model_size: 256
+    warmup_steps: 25000
+
+# minibatch related
+batch_type: folded
+batch_size: 128
+
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+num_att_plot: 0
+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