From 8bf745a55e459f0b91d744184ba9fce66f0e6fa7 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 23 五月 2023 19:37:26 +0800
Subject: [PATCH] update repo
---
egs/aishell/data2vec_transformer_finetune/run.sh | 4 ++--
egs/aishell/paraformerbert/run.sh | 4 ++--
egs/aishell2/transformer/utils/compute_cmvn.sh | 2 +-
egs/aishell2/conformer/run.sh | 4 ++--
egs/librispeech/conformer/run.sh | 4 ++--
egs/aishell2/paraformerbert/run.sh | 4 ++--
egs/librispeech_100h/conformer/run.sh | 4 ++--
egs/aishell/conformer/run.sh | 4 ++--
egs/aishell/transformer/run.sh | 4 ++--
egs/aishell/transformer/utils/compute_cmvn.sh | 2 +-
egs/aishell/data2vec_paraformer_finetune/run.sh | 4 ++--
egs/aishell2/transformer/run.sh | 4 ++--
egs/aishell/paraformer/run.sh | 4 ++--
egs/aishell2/data2vec_pretrain/run.sh | 2 +-
docs/academic_recipe/asr_recipe.md | 2 +-
egs/aishell2/paraformer/run.sh | 4 ++--
16 files changed, 28 insertions(+), 28 deletions(-)
diff --git a/docs/academic_recipe/asr_recipe.md b/docs/academic_recipe/asr_recipe.md
index 128b85c..f2ac3e8 100644
--- a/docs/academic_recipe/asr_recipe.md
+++ b/docs/academic_recipe/asr_recipe.md
@@ -47,7 +47,7 @@
These two files both have two columns, while the first column is wav ids and the second column is the corresponding wav paths/label tokens.
### Stage 1: Feature and CMVN Generation
-This stage computes CMVN based on `train` dataset, which is used in the following stages. Users can set `nj` to control the number of jobs for computing CMVN. The generated CMVN file is saved as `$feats_dir/data/train/cmvn/cmvn.mvn`.
+This stage computes CMVN based on `train` dataset, which is used in the following stages. Users can set `nj` to control the number of jobs for computing CMVN. The generated CMVN file is saved as `$feats_dir/data/train/cmvn/am.mvn`.
### Stage 2: Dictionary Preparation
This stage processes the dictionary, which is used as a mapping between label characters and integer indices during ASR training. The processed dictionary file is saved as `$feats_dir/data/$lang_toekn_list/$token_type/tokens.txt`. An example of `tokens.txt` is as follows:
diff --git a/egs/aishell/conformer/run.sh b/egs/aishell/conformer/run.sh
index 3c05006..f73605c 100755
--- a/egs/aishell/conformer/run.sh
+++ b/egs/aishell/conformer/run.sh
@@ -136,7 +136,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -186,7 +186,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell/data2vec_paraformer_finetune/run.sh b/egs/aishell/data2vec_paraformer_finetune/run.sh
index 147add1..ff74714 100755
--- a/egs/aishell/data2vec_paraformer_finetune/run.sh
+++ b/egs/aishell/data2vec_paraformer_finetune/run.sh
@@ -141,7 +141,7 @@
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
--init_param ${init_param} \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
--config $asr_config \
@@ -190,7 +190,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
diff --git a/egs/aishell/data2vec_transformer_finetune/run.sh b/egs/aishell/data2vec_transformer_finetune/run.sh
index af0b8c1..6ac4fa9 100755
--- a/egs/aishell/data2vec_transformer_finetune/run.sh
+++ b/egs/aishell/data2vec_transformer_finetune/run.sh
@@ -141,7 +141,7 @@
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
--init_param ${init_param} \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -191,7 +191,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell/paraformer/run.sh b/egs/aishell/paraformer/run.sh
index 39ce85a..474c199 100755
--- a/egs/aishell/paraformer/run.sh
+++ b/egs/aishell/paraformer/run.sh
@@ -136,7 +136,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -186,7 +186,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell/paraformerbert/run.sh b/egs/aishell/paraformerbert/run.sh
index 5562f15..90d9aee 100755
--- a/egs/aishell/paraformerbert/run.sh
+++ b/egs/aishell/paraformerbert/run.sh
@@ -147,7 +147,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text,embeds.scp" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -197,7 +197,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell/transformer/run.sh b/egs/aishell/transformer/run.sh
index 3db8a08..011852f 100755
--- a/egs/aishell/transformer/run.sh
+++ b/egs/aishell/transformer/run.sh
@@ -136,7 +136,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -186,7 +186,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell/transformer/utils/compute_cmvn.sh b/egs/aishell/transformer/utils/compute_cmvn.sh
index 7663df9..75d88a2 100755
--- a/egs/aishell/transformer/utils/compute_cmvn.sh
+++ b/egs/aishell/transformer/utils/compute_cmvn.sh
@@ -29,6 +29,6 @@
python utils/combine_cmvn_file.py --dim ${feats_dim} --cmvn_dir $split_dir --nj $nj --output_dir ${fbankdir}/cmvn
-python utils/cmvn_converter.py --cmvn_json ${fbankdir}/cmvn/cmvn.json --am_mvn ${fbankdir}/cmvn/cmvn.mvn
+python utils/cmvn_converter.py --cmvn_json ${fbankdir}/cmvn/cmvn.json --am_mvn ${fbankdir}/cmvn/am.mvn
echo "$0: Succeeded compute global cmvn"
diff --git a/egs/aishell2/conformer/run.sh b/egs/aishell2/conformer/run.sh
index ae57431..44070ed 100755
--- a/egs/aishell2/conformer/run.sh
+++ b/egs/aishell2/conformer/run.sh
@@ -138,7 +138,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
@@ -189,7 +189,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell2/data2vec_pretrain/run.sh b/egs/aishell2/data2vec_pretrain/run.sh
index 9334a4b..ee6c7d3 100755
--- a/egs/aishell2/data2vec_pretrain/run.sh
+++ b/egs/aishell2/data2vec_pretrain/run.sh
@@ -109,7 +109,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
diff --git a/egs/aishell2/paraformer/run.sh b/egs/aishell2/paraformer/run.sh
index 83e49d0..7656e8d 100755
--- a/egs/aishell2/paraformer/run.sh
+++ b/egs/aishell2/paraformer/run.sh
@@ -138,7 +138,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
@@ -189,7 +189,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell2/paraformerbert/run.sh b/egs/aishell2/paraformerbert/run.sh
index a5e5ba9..86fdc9b 100755
--- a/egs/aishell2/paraformerbert/run.sh
+++ b/egs/aishell2/paraformerbert/run.sh
@@ -148,7 +148,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text,embeds.scp" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
@@ -199,7 +199,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell2/transformer/run.sh b/egs/aishell2/transformer/run.sh
index 6e5c82a..67ac2dc 100755
--- a/egs/aishell2/transformer/run.sh
+++ b/egs/aishell2/transformer/run.sh
@@ -138,7 +138,7 @@
--train_set ${train_set} \
--valid_set ${valid_set} \
--data_file_names "wav.scp,text" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--dataset_type $dataset_type \
--resume true \
@@ -189,7 +189,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/aishell2/transformer/utils/compute_cmvn.sh b/egs/aishell2/transformer/utils/compute_cmvn.sh
index 7663df9..75d88a2 100755
--- a/egs/aishell2/transformer/utils/compute_cmvn.sh
+++ b/egs/aishell2/transformer/utils/compute_cmvn.sh
@@ -29,6 +29,6 @@
python utils/combine_cmvn_file.py --dim ${feats_dim} --cmvn_dir $split_dir --nj $nj --output_dir ${fbankdir}/cmvn
-python utils/cmvn_converter.py --cmvn_json ${fbankdir}/cmvn/cmvn.json --am_mvn ${fbankdir}/cmvn/cmvn.mvn
+python utils/cmvn_converter.py --cmvn_json ${fbankdir}/cmvn/cmvn.json --am_mvn ${fbankdir}/cmvn/am.mvn
echo "$0: Succeeded compute global cmvn"
diff --git a/egs/librispeech/conformer/run.sh b/egs/librispeech/conformer/run.sh
index b44dad3..e54b764 100755
--- a/egs/librispeech/conformer/run.sh
+++ b/egs/librispeech/conformer/run.sh
@@ -150,7 +150,7 @@
--data_dir ${feats_dir}/data \
--train_set ${train_set} \
--valid_set ${valid_set} \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -201,7 +201,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
diff --git a/egs/librispeech_100h/conformer/run.sh b/egs/librispeech_100h/conformer/run.sh
index f0db69c..8df0278 100755
--- a/egs/librispeech_100h/conformer/run.sh
+++ b/egs/librispeech_100h/conformer/run.sh
@@ -146,7 +146,7 @@
--data_dir ${feats_dir}/data \
--train_set ${train_set} \
--valid_set ${valid_set} \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--speed_perturb ${speed_perturb} \
--resume true \
--output_dir ${exp_dir}/exp/${model_dir} \
@@ -197,7 +197,7 @@
--njob ${njob} \
--gpuid_list ${gpuid_list} \
--data_path_and_name_and_type "${_data}/${scp},speech,${type}" \
- --cmvn_file ${feats_dir}/data/${train_set}/cmvn/cmvn.mvn \
+ --cmvn_file ${feats_dir}/data/${train_set}/cmvn/am.mvn \
--key_file "${_logdir}"/keys.JOB.scp \
--asr_train_config "${asr_exp}"/config.yaml \
--asr_model_file "${asr_exp}"/"${inference_asr_model}" \
--
Gitblit v1.9.1