From cc2c1d1d53dea5d2c45f858d1baa5bd279f47987 Mon Sep 17 00:00:00 2001 From: nichongjia-2007 <nichongjia@gmail.com> Date: 星期三, 31 五月 2023 14:39:25 +0800 Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR --- egs/wenetspeech/conformer/conf/train_asr_conformer.yaml | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 104 insertions(+), 0 deletions(-) diff --git a/egs/wenetspeech/conformer/conf/train_asr_conformer.yaml b/egs/wenetspeech/conformer/conf/train_asr_conformer.yaml new file mode 100644 index 0000000..a9658b8 --- /dev/null +++ b/egs/wenetspeech/conformer/conf/train_asr_conformer.yaml @@ -0,0 +1,104 @@ +# network architecture +# encoder related +encoder: conformer +encoder_conf: + output_size: 512 # dimension of attention + attention_heads: 8 + 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 + rel_pos_type: latest + 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 + +# decoder related +decoder: transformer +decoder_conf: + attention_heads: 8 + linear_units: 2048 + num_blocks: 6 + dropout_rate: 0.1 + positional_dropout_rate: 0.1 + self_attention_dropout_rate: 0.0 + src_attention_dropout_rate: 0.0 + +# CTC realted +ctc_conf: + ignore_nan_grad: true + +# 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 + +# hybrid CTC/attention +model_conf: + ctc_weight: 0.3 + lsm_weight: 0.1 # label smoothing option + length_normalized_loss: false + +# optimization related +accum_grad: 4 +grad_clip: 5 +patience: none +max_epoch: 30 +val_scheduler_criterion: + - valid + - acc +best_model_criterion: +- - valid + - acc + - max +keep_nbest_models: 10 + +optim: adam +optim_conf: + lr: 0.0015 +scheduler: warmuplr +scheduler_conf: + warmup_steps: 30000 + +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 + +dataset_conf: + data_names: speech,text + data_types: sound,text_nospace + shuffle: True + shuffle_conf: + shuffle_size: 2048 + sort_size: 500 + batch_conf: + batch_type: token + batch_size: 32000 + num_workers: 8 + +log_interval: 50 +normalize: None -- Gitblit v1.9.1