From c83c406b72623deb973d391635475c5dfd9f8b93 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 06 七月 2023 17:12:19 +0800
Subject: [PATCH] update eend_ola
---
egs/callhome/eend_ola/local/model_averaging.py | 28 +++
egs/callhome/eend_ola/utils | 1
egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_2spkr.yaml | 52 ++++++
egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr_chunk2000.yaml | 44 +++++
egs/callhome/eend_ola/run.sh | 242 ++++++++++++++++++++++++++++++
egs/callhome/eend_ola/path.sh | 6
egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr.yaml | 52 ++++++
egs/callhome/eend_ola/conf/train_diar_eend_ola_callhome_chunk2000.yaml | 45 +++++
8 files changed, 470 insertions(+), 0 deletions(-)
diff --git a/egs/callhome/eend_ola/conf/train_diar_eend_ola_callhome_chunk2000.yaml b/egs/callhome/eend_ola/conf/train_diar_eend_ola_callhome_chunk2000.yaml
new file mode 100644
index 0000000..71ea9f0
--- /dev/null
+++ b/egs/callhome/eend_ola/conf/train_diar_eend_ola_callhome_chunk2000.yaml
@@ -0,0 +1,45 @@
+# network architecture
+# encoder related
+encoder: eend_ola_transformer
+encoder_conf:
+ idim: 345
+ n_layers: 4
+ n_units: 256
+
+# encoder-decoder attractor related
+encoder_decoder_attractor: eda
+encoder_decoder_attractor_conf:
+ n_units: 256
+
+# model related
+model: eend_ola_similar_eend
+model_conf:
+ attractor_loss_weight: 0.01
+ max_n_speaker: 8
+
+# optimization related
+accum_grad: 1
+grad_clip: 5
+max_epoch: 100
+val_scheduler_criterion:
+ - valid
+ - loss
+best_model_criterion:
+- - valid
+ - loss
+ - min
+keep_nbest_models: 100
+
+optim: adam
+optim_conf:
+ lr: 0.00001
+
+dataset_conf:
+ data_names: speech_speaker_labels
+ data_types: kaldi_ark
+ batch_conf:
+ batch_type: unsorted
+ batch_size: 8
+ num_workers: 8
+
+log_interval: 50
\ No newline at end of file
diff --git a/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_2spkr.yaml b/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_2spkr.yaml
new file mode 100644
index 0000000..baf4342
--- /dev/null
+++ b/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_2spkr.yaml
@@ -0,0 +1,52 @@
+# network architecture
+# encoder related
+encoder: eend_ola_transformer
+encoder_conf:
+ idim: 345
+ n_layers: 4
+ n_units: 256
+
+# encoder-decoder attractor related
+encoder_decoder_attractor: eda
+encoder_decoder_attractor_conf:
+ n_units: 256
+
+# model related
+model: eend_ola_similar_eend
+model_conf:
+ max_n_speaker: 8
+
+# optimization related
+accum_grad: 1
+grad_clip: 5
+max_epoch: 100
+val_scheduler_criterion:
+ - valid
+ - loss
+best_model_criterion:
+- - valid
+ - loss
+ - min
+keep_nbest_models: 100
+
+optim: adam
+optim_conf:
+ lr: 1.0
+ betas:
+ - 0.9
+ - 0.98
+ eps: 1.0e-9
+scheduler: noamlr
+scheduler_conf:
+ model_size: 256
+ warmup_steps: 100000
+
+dataset_conf:
+ data_names: speech_speaker_labels
+ data_types: kaldi_ark
+ batch_conf:
+ batch_type: unsorted
+ batch_size: 64
+ num_workers: 8
+
+log_interval: 50
\ No newline at end of file
diff --git a/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr.yaml b/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr.yaml
new file mode 100644
index 0000000..83a6eee
--- /dev/null
+++ b/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr.yaml
@@ -0,0 +1,52 @@
+# network architecture
+# encoder related
+encoder: eend_ola_transformer
+encoder_conf:
+ idim: 345
+ n_layers: 4
+ n_units: 256
+
+# encoder-decoder attractor related
+encoder_decoder_attractor: eda
+encoder_decoder_attractor_conf:
+ n_units: 256
+
+# model related
+model: eend_ola_similar_eend
+model_conf:
+ max_n_speaker: 8
+
+# optimization related
+accum_grad: 1
+grad_clip: 5
+max_epoch: 25
+val_scheduler_criterion:
+ - valid
+ - loss
+best_model_criterion:
+- - valid
+ - loss
+ - min
+keep_nbest_models: 100
+
+optim: adam
+optim_conf:
+ lr: 1.0
+ betas:
+ - 0.9
+ - 0.98
+ eps: 1.0e-9
+scheduler: noamlr
+scheduler_conf:
+ model_size: 256
+ warmup_steps: 100000
+
+dataset_conf:
+ data_names: speech_speaker_labels
+ data_types: kaldi_ark
+ batch_conf:
+ batch_type: unsorted
+ batch_size: 64
+ num_workers: 8
+
+log_interval: 50
\ No newline at end of file
diff --git a/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr_chunk2000.yaml b/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr_chunk2000.yaml
new file mode 100644
index 0000000..f478504
--- /dev/null
+++ b/egs/callhome/eend_ola/conf/train_diar_eend_ola_simu_allspkr_chunk2000.yaml
@@ -0,0 +1,44 @@
+# network architecture
+# encoder related
+encoder: eend_ola_transformer
+encoder_conf:
+ idim: 345
+ n_layers: 4
+ n_units: 256
+
+# encoder-decoder attractor related
+encoder_decoder_attractor: eda
+encoder_decoder_attractor_conf:
+ n_units: 256
+
+# model related
+model: eend_ola_similar_eend
+model_conf:
+ max_n_speaker: 8
+
+# optimization related
+accum_grad: 1
+grad_clip: 5
+max_epoch: 1
+val_scheduler_criterion:
+ - valid
+ - loss
+best_model_criterion:
+- - valid
+ - loss
+ - min
+keep_nbest_models: 100
+
+optim: adam
+optim_conf:
+ lr: 0.00001
+
+dataset_conf:
+ data_names: speech_speaker_labels
+ data_types: kaldi_ark
+ batch_conf:
+ batch_type: unsorted
+ batch_size: 8
+ num_workers: 8
+
+log_interval: 50
\ No newline at end of file
diff --git a/egs/callhome/eend_ola/local/model_averaging.py b/egs/callhome/eend_ola/local/model_averaging.py
new file mode 100644
index 0000000..1871cd9
--- /dev/null
+++ b/egs/callhome/eend_ola/local/model_averaging.py
@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+
+import argparse
+
+import torch
+
+
+def average_model(input_files, output_file):
+ output_model = {}
+ for ckpt_path in input_files:
+ model_params = torch.load(ckpt_path, map_location="cpu")
+ for key, value in model_params.items():
+ if key not in output_model:
+ output_model[key] = value
+ else:
+ output_model[key] += value
+ for key in output_model.keys():
+ output_model[key] /= len(input_files)
+ torch.save(output_model, output_file)
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument("output_file")
+ parser.add_argument("input_files", nargs='+')
+ args = parser.parse_args()
+
+ average_model(args.input_files, args.output_file)
\ No newline at end of file
diff --git a/egs/callhome/eend_ola/path.sh b/egs/callhome/eend_ola/path.sh
new file mode 100755
index 0000000..ea3c0be
--- /dev/null
+++ b/egs/callhome/eend_ola/path.sh
@@ -0,0 +1,6 @@
+export FUNASR_DIR=$PWD/../../..
+
+# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
+export PYTHONIOENCODING=UTF-8
+export PYTHONPATH=../../../:$PYTHONPATH
+export PATH=$FUNASR_DIR/funasr/bin:$PATH
diff --git a/egs/callhome/eend_ola/run.sh b/egs/callhome/eend_ola/run.sh
new file mode 100644
index 0000000..8936137
--- /dev/null
+++ b/egs/callhome/eend_ola/run.sh
@@ -0,0 +1,242 @@
+#!/usr/bin/env bash
+
+. ./path.sh || exit 1;
+
+# machines configuration
+CUDA_VISIBLE_DEVICES="7"
+gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
+count=1
+
+# general configuration
+simu_feats_dir="/nfs/wangjiaming.wjm/EEND_ARK_DATA/dump/simu_data/data"
+simu_feats_dir_chunk2000="/nfs/wangjiaming.wjm/EEND_ARK_DATA/dump/simu_data_chunk2000/data"
+callhome_feats_dir_chunk2000="/nfs/wangjiaming.wjm/EEND_ARK_DATA/dump/callhome_chunk2000/data"
+simu_train_dataset=train
+simu_valid_dataset=dev
+callhome_train_dataset=callhome1_allspk
+callhome_valid_dataset=callhome2_allspk
+callhome2_wav_scp_file=wav.scp
+
+# model average
+simu_average_2spkr_start=91
+simu_average_2spkr_end=100
+simu_average_allspkr_start=16
+simu_average_allspkr_end=25
+callhome_average_start=91
+callhome_average_end=100
+
+exp_dir="."
+input_size=345
+stage=1
+stop_stage=4
+
+# exp tag
+tag="exp_fix"
+
+. utils/parse_options.sh || exit 1;
+
+# Set bash to 'debug' mode, it will exit on :
+# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
+set -e
+set -u
+set -o pipefail
+
+simu_2spkr_diar_config=conf/train_diar_eend_ola_simu_2spkr.yaml
+simu_allspkr_diar_config=conf/train_diar_eend_ola_simu_allspkr.yaml
+simu_allspkr_chunk2000_diar_config=conf/train_diar_eend_ola_simu_allspkr_chunk2000.yaml
+callhome_diar_config=conf/train_diar_eend_ola_callhome_chunk2000.yaml
+simu_2spkr_model_dir="baseline_$(basename "${simu_2spkr_diar_config}" .yaml)_${tag}"
+simu_allspkr_model_dir="baseline_$(basename "${simu_allspkr_diar_config}" .yaml)_${tag}"
+simu_allspkr_chunk2000_model_dir="baseline_$(basename "${simu_allspkr_chunk2000_diar_config}" .yaml)_${tag}"
+callhome_model_dir="baseline_$(basename "${callhome_diar_config}" .yaml)_${tag}"
+
+# Prepare data for training and inference
+if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
+ echo "stage 0: Prepare data for training and inference"
+fi
+
+# Training on simulated two-speaker data
+world_size=$gpu_num
+simu_2spkr_ave_id=avg${simu_average_2spkr_start}-${simu_average_2spkr_end}
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+ echo "stage 1: Training on simulated two-speaker data"
+ mkdir -p ${exp_dir}/exp/${simu_2spkr_model_dir}
+ mkdir -p ${exp_dir}/exp/${simu_2spkr_model_dir}/log
+ INIT_FILE=${exp_dir}/exp/${simu_2spkr_model_dir}/ddp_init
+ if [ -f $INIT_FILE ];then
+ rm -f $INIT_FILE
+ fi
+ init_method=file://$(readlink -f $INIT_FILE)
+ echo "$0: init method is $init_method"
+ for ((i = 0; i < $gpu_num; ++i)); do
+ {
+ rank=$i
+ local_rank=$i
+ gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
+ train.py \
+ --task_name diar \
+ --gpu_id $gpu_id \
+ --use_preprocessor false \
+ --input_size $input_size \
+ --data_dir ${simu_feats_dir} \
+ --train_set ${simu_train_dataset} \
+ --valid_set ${simu_valid_dataset} \
+ --data_file_names "feats_2spkr.scp" \
+ --resume true \
+ --output_dir ${exp_dir}/exp/${simu_2spkr_model_dir} \
+ --config $simu_2spkr_diar_config \
+ --ngpu $gpu_num \
+ --num_worker_count $count \
+ --dist_init_method $init_method \
+ --dist_world_size $world_size \
+ --dist_rank $rank \
+ --local_rank $local_rank 1> ${exp_dir}/exp/${simu_2spkr_model_dir}/log/train.log.$i 2>&1
+ } &
+ done
+ wait
+ echo "averaging model parameters into ${exp_dir}/exp/$simu_2spkr_model_dir/$simu_2spkr_ave_id.pb"
+ models=`eval echo ${exp_dir}/exp/${simu_2spkr_model_dir}/{$simu_average_2spkr_start..$simu_average_2spkr_end}epoch.pb`
+ python local/model_averaging.py ${exp_dir}/exp/${simu_2spkr_model_dir}/$simu_2spkr_ave_id.pb $models
+fi
+
+# Training on simulated all-speaker data
+world_size=$gpu_num
+simu_allspkr_ave_id=avg${simu_average_allspkr_start}-${simu_average_allspkr_end}
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+ echo "stage 2: Training on simulated all-speaker data"
+ mkdir -p ${exp_dir}/exp/${simu_allspkr_model_dir}
+ mkdir -p ${exp_dir}/exp/${simu_allspkr_model_dir}/log
+ INIT_FILE=${exp_dir}/exp/${simu_allspkr_model_dir}/ddp_init
+ if [ -f $INIT_FILE ];then
+ rm -f $INIT_FILE
+ fi
+ init_method=file://$(readlink -f $INIT_FILE)
+ echo "$0: init method is $init_method"
+ for ((i = 0; i < $gpu_num; ++i)); do
+ {
+ rank=$i
+ local_rank=$i
+ gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
+ train.py \
+ --task_name diar \
+ --gpu_id $gpu_id \
+ --use_preprocessor false \
+ --input_size $input_size \
+ --data_dir ${simu_feats_dir} \
+ --train_set ${simu_train_dataset} \
+ --valid_set ${simu_valid_dataset} \
+ --data_file_names "feats.scp" \
+ --resume true \
+ --init_param ${exp_dir}/exp/${simu_2spkr_model_dir}/$simu_2spkr_ave_id.pb \
+ --output_dir ${exp_dir}/exp/${simu_allspkr_model_dir} \
+ --config $simu_allspkr_diar_config \
+ --ngpu $gpu_num \
+ --num_worker_count $count \
+ --dist_init_method $init_method \
+ --dist_world_size $world_size \
+ --dist_rank $rank \
+ --local_rank $local_rank 1> ${exp_dir}/exp/${simu_allspkr_model_dir}/log/train.log.$i 2>&1
+ } &
+ done
+ wait
+ echo "averaging model parameters into ${exp_dir}/exp/$simu_allspkr_model_dir/$simu_allspkr_ave_id.pb"
+ models=`eval echo ${exp_dir}/exp/${simu_allspkr_model_dir}/{$simu_average_allspkr_start..$simu_average_allspkr_end}epoch.pb`
+ python local/model_averaging.py ${exp_dir}/exp/${simu_allspkr_model_dir}/$simu_allspkr_ave_id.pb $models
+fi
+
+# Training on simulated all-speaker data with chunk_size=2000
+world_size=$gpu_num
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+ echo "stage 3: Training on simulated all-speaker data with chunk_size=2000"
+ mkdir -p ${exp_dir}/exp/${simu_allspkr_chunk2000_model_dir}
+ mkdir -p ${exp_dir}/exp/${simu_allspkr_chunk2000_model_dir}/log
+ INIT_FILE=${exp_dir}/exp/${simu_allspkr_chunk2000_model_dir}/ddp_init
+ if [ -f $INIT_FILE ];then
+ rm -f $INIT_FILE
+ fi
+ init_method=file://$(readlink -f $INIT_FILE)
+ echo "$0: init method is $init_method"
+ for ((i = 0; i < $gpu_num; ++i)); do
+ {
+ rank=$i
+ local_rank=$i
+ gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
+ train.py \
+ --task_name diar \
+ --gpu_id $gpu_id \
+ --use_preprocessor false \
+ --input_size $input_size \
+ --data_dir ${simu_feats_dir_chunk2000} \
+ --train_set ${simu_train_dataset} \
+ --valid_set ${simu_valid_dataset} \
+ --data_file_names "feats.scp" \
+ --resume true \
+ --init_param ${exp_dir}/exp/${simu_allspkr_model_dir}/$simu_allspkr_ave_id.pb \
+ --output_dir ${exp_dir}/exp/${simu_allspkr_chunk2000_model_dir} \
+ --config $simu_allspkr_chunk2000_diar_config \
+ --ngpu $gpu_num \
+ --num_worker_count $count \
+ --dist_init_method $init_method \
+ --dist_world_size $world_size \
+ --dist_rank $rank \
+ --local_rank $local_rank 1> ${exp_dir}/exp/${simu_allspkr_chunk2000_model_dir}/log/train.log.$i 2>&1
+ } &
+ done
+ wait
+fi
+
+# Training on callhome all-speaker data with chunk_size=2000
+world_size=$gpu_num
+callhome_ave_id=avg${callhome_average_start}-${callhome_average_end}
+if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
+ echo "stage 4: Training on callhome all-speaker data with chunk_size=2000"
+ mkdir -p ${exp_dir}/exp/${callhome_model_dir}
+ mkdir -p ${exp_dir}/exp/${callhome_model_dir}/log
+ INIT_FILE=${exp_dir}/exp/${callhome_model_dir}/ddp_init
+ if [ -f $INIT_FILE ];then
+ rm -f $INIT_FILE
+ fi
+ init_method=file://$(readlink -f $INIT_FILE)
+ echo "$0: init method is $init_method"
+ for ((i = 0; i < $gpu_num; ++i)); do
+ {
+ rank=$i
+ local_rank=$i
+ gpu_id=$(echo $CUDA_VISIBLE_DEVICES | cut -d',' -f$[$i+1])
+ train.py \
+ --task_name diar \
+ --gpu_id $gpu_id \
+ --use_preprocessor false \
+ --input_size $input_size \
+ --data_dir ${callhome_feats_dir_chunk2000} \
+ --train_set ${callhome_train_dataset} \
+ --valid_set ${callhome_valid_dataset} \
+ --data_file_names "feats.scp" \
+ --resume true \
+ --init_param ${exp_dir}/exp/${simu_allspkr_chunk2000_model_dir}/1epoch.pb \
+ --output_dir ${exp_dir}/exp/${callhome_model_dir} \
+ --config $callhome_diar_config \
+ --ngpu $gpu_num \
+ --num_worker_count $count \
+ --dist_init_method $init_method \
+ --dist_world_size $world_size \
+ --dist_rank $rank \
+ --local_rank $local_rank 1> ${exp_dir}/exp/${callhome_model_dir}/log/train.log.$i 2>&1
+ } &
+ done
+ wait
+ echo "averaging model parameters into ${exp_dir}/exp/$callhome_model_dir/$callhome_ave_id.pb"
+ models=`eval echo ${exp_dir}/exp/${callhome_model_dir}/{$callhome_average_start..$callhome_average_end}epoch.pb`
+ python local/model_averaging.py ${exp_dir}/exp/${callhome_model_dir}/$callhome_ave_id.pb $models
+fi
+
+## inference
+#if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
+# echo "Inference"
+# mkdir -p ${exp_dir}/exp/${callhome_model_dir}/inference/log
+# CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES python local/infer.py \
+# --config_file ${exp_dir}/exp/${callhome_model_dir}/config.yaml \
+# --model_file ${exp_dir}/exp/${callhome_model_dir}/$callhome_ave_id.pb \
+# --output_rttm_file ${exp_dir}/exp/${callhome_model_dir}/inference/rttm \
+# --wav_scp_file ${callhome_feats_dir_chunk2000}/${callhome_valid_dataset}/${callhome2_wav_scp_file} 1> ${exp_dir}/exp/${callhome_model_dir}/inference/log/infer.log 2>&1
+#fi
\ No newline at end of file
diff --git a/egs/callhome/eend_ola/utils b/egs/callhome/eend_ola/utils
new file mode 120000
index 0000000..fe070dd
--- /dev/null
+++ b/egs/callhome/eend_ola/utils
@@ -0,0 +1 @@
+../../aishell/transformer/utils
\ No newline at end of file
--
Gitblit v1.9.1