From 580b11b57ac4b62f7e2acda73813a4e10e8e4cd3 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 10 十月 2023 17:17:29 +0800
Subject: [PATCH] v0.8.0
---
egs/aishell/rnnt/conf/train_conformer_rnnt_unified.yaml | 81 ++++++++++++++++++++++++----------------
1 files changed, 48 insertions(+), 33 deletions(-)
diff --git a/egs/aishell/rnnt/conf/train_conformer_rnnt_unified.yaml b/egs/aishell/rnnt/conf/train_conformer_rnnt_unified.yaml
index ef37b97..a1f27a3 100644
--- a/egs/aishell/rnnt/conf/train_conformer_rnnt_unified.yaml
+++ b/egs/aishell/rnnt/conf/train_conformer_rnnt_unified.yaml
@@ -1,54 +1,57 @@
+encoder: chunk_conformer
encoder_conf:
- main_conf:
- pos_wise_act_type: swish
- pos_enc_dropout_rate: 0.3
- conv_mod_act_type: swish
+ activation_type: swish
+ positional_dropout_rate: 0.5
time_reduction_factor: 2
unified_model_training: true
default_chunk_size: 16
jitter_range: 4
left_chunk_size: 1
- input_conf:
- block_type: conv2d
- conv_size: 512
+ embed_vgg_like: false
subsampling_factor: 4
- num_frame: 1
- body_conf:
- - block_type: conformer
- linear_size: 2048
- hidden_size: 512
- heads: 8
- dropout_rate: 0.3
- pos_wise_dropout_rate: 0.3
- att_dropout_rate: 0.3
- conv_mod_kernel_size: 15
+ linear_units: 2048
+ output_size: 512
+ attention_heads: 8
+ dropout_rate: 0.5
+ positional_dropout_rate: 0.5
+ attention_dropout_rate: 0.5
+ cnn_module_kernel: 15
num_blocks: 12
# decoder related
-decoder: rnn
-decoder_conf:
+rnnt_decoder: rnnt
+rnnt_decoder_conf:
embed_size: 512
hidden_size: 512
- embed_dropout_rate: 0.2
- dropout_rate: 0.1
-
+ embed_dropout_rate: 0.5
+ dropout_rate: 0.5
joint_network_conf:
joint_space_size: 512
+# frontend related
+frontend: wav_frontend
+frontend_conf:
+ fs: 16000
+ window: hamming
+ n_mels: 80
+ frame_length: 25
+ frame_shift: 10
+ lfr_m: 1
+ lfr_n: 1
+
+
# Auxiliary CTC
+model: rnnt_unified
model_conf:
auxiliary_ctc_weight: 0.0
# minibatch related
use_amp: true
-batch_type: numel
-batch_bins: 1600000
-num_workers: 16
# optimization related
accum_grad: 1
grad_clip: 5
-max_epoch: 80
+max_epoch: 120
val_scheduler_criterion:
- valid
- loss
@@ -56,16 +59,14 @@
- - valid
- cer_transducer_chunk
- min
-keep_nbest_models: 5
+keep_nbest_models: 10
optim: adam
optim_conf:
- lr: 0.0003
+ lr: 0.001
scheduler: warmuplr
scheduler_conf:
warmup_steps: 25000
-
-normalize: None
specaug: specaug
specaug_conf:
@@ -75,10 +76,24 @@
apply_freq_mask: true
freq_mask_width_range:
- 0
- - 30
+ - 40
num_freq_mask: 2
apply_time_mask: true
time_mask_width_range:
- 0
- - 40
- num_time_mask: 2
+ - 50
+ num_time_mask: 5
+
+dataset_conf:
+ data_names: speech,text
+ data_types: sound,text
+ shuffle: True
+ shuffle_conf:
+ shuffle_size: 2048
+ sort_size: 500
+ batch_conf:
+ batch_type: token
+ batch_size: 16000
+ num_workers: 8
+
+log_interval: 50
--
Gitblit v1.9.1