From 8acfbdc4f8d094eddbbd1375d6707a527ebbca34 Mon Sep 17 00:00:00 2001
From: 志浩 <neo.dzh@alibaba-inc.com>
Date: 星期三, 02 八月 2023 16:20:38 +0800
Subject: [PATCH] TOLD/SOND: add download pretrained model
---
egs/callhome/diarization/sond/finetune.sh | 23 +++++++++++++++++++----
1 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/egs/callhome/diarization/sond/finetune.sh b/egs/callhome/diarization/sond/finetune.sh
index 5a4842d..56e80de 100644
--- a/egs/callhome/diarization/sond/finetune.sh
+++ b/egs/callhome/diarization/sond/finetune.sh
@@ -177,12 +177,15 @@
sv_exp_dir=exp/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch
if [ ! -e ${sv_exp_dir} ]; then
+ echo "start to download sv models"
git lfs install
git clone https://www.modelscope.cn/damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch.git
mv speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch ${expdir}/
+ echo "Done."
fi
for dset in callhome1/nonoverlap_0s callhome2/nonoverlap_0s; do
+ echo "Start to extract speaker embeddings for ${dset}"
key_file=${datadir}/${dset}/wav.scp
num_scp_file="$(<${key_file} wc -l)"
_nj=$([ $inference_nj -le $num_scp_file ] && echo "$inference_nj" || echo "$num_scp_file")
@@ -207,6 +210,9 @@
--sv_model_file ${sv_exp_dir}/sv.pth \
--output_dir "${_logdir}"/output.JOB
cat ${_logdir}/output.*/xvector.scp | sort > ${datadir}/${dset}/utt2xvec
+
+ python script/calc_num_frames.py ${key_file} ${datadir}/${dset}/utt2num_frames
+ echo "Done."
done
fi
@@ -219,7 +225,7 @@
python -Wignore script/calc_real_meeting_frame_labels.py \
${datadir}/${dset} ${dumpdir}/${dset}/labels \
--n_spk 8 --frame_shift 0.01 --nj 16 --sr 8000
- find `pwd`/${dumpdir}/${dset}/labels -iname "*.lbl.mat" | awk -F'[/.]' '{print $(NF-2),$0}' | sort > ${datadir}/${dset}/labels.scp
+ find `pwd`/${dumpdir}/${dset}/labels/ -iname "*.lbl.mat" | awk -F'[/.]' '{print $(NF-2),$0}' | sort > ${datadir}/${dset}/labels.scp
done
fi
@@ -237,7 +243,7 @@
echo "Stage 6: start to dump for callhome1."
python -Wignore script/dump_meeting_chunks.py --dir ${data_dir} \
- --out ${dumpdir}/callhome1/dumped_files/data --n_spk 16 --no_pbar --sr 8000 --mode test \
+ --out ${dumpdir}/callhome1/dumped_files/data --n_spk 16 --no_pbar --sr 8000 --mode train \
--chunk_size 1600 --chunk_shift 400 --add_mid_to_speaker true
mkdir -p ${datadir}/callhome1/dumped_files
@@ -274,6 +280,15 @@
# Finetune model on callhome1, this will take about 1.5 hours.
if [ ${stage} -le 7 ] && [ ${stop_stage} -ge 7 ]; then
echo "Stage 7: Finetune pretrained model on callhome1."
+
+ if [ ! -e ${expdir}/speech_diarization_sond-en-us-swbd_sre-8k-n16k4-pytorch ]; then
+ echo "start to download pretrained models"
+ git lfs install
+ git clone https://www.modelscope.cn/damo/speech_diarization_sond-en-us-swbd_sre-8k-n16k4-pytorch.git
+ mv speech_diarization_sond-en-us-swbd_sre-8k-n16k4-pytorch ${expdir}/
+ echo "Done."
+ fi
+
world_size=$gpu_num # run on one machine
mkdir -p ${expdir}/${model_dir}
mkdir -p ${expdir}/${model_dir}/log
@@ -314,7 +329,7 @@
--valid_data_path_and_name_and_type ${datadir}/${valid_set}/dumped_files/profile.scp,profile,kaldi_ark \
--valid_data_path_and_name_and_type ${datadir}/${valid_set}/dumped_files/label.scp,binary_labels,kaldi_ark \
--valid_shape_file ${expdir}/${valid_set}_states/speech_shape \
- --init_param exp/pretrained_models/phase2.pth \
+ --init_param ${expdir}/speech_diarization_sond-en-us-swbd_sre-8k-n16k4-pytorch/sond.pth \
--unused_parameters true \
${init_opt} \
${freeze_opt} \
@@ -383,7 +398,7 @@
# Scoring for finetuned model, you may get a DER like:
# oracle_vad | system_vad
-# 7.28 | 8.06
+# 7.27 | 8.08
if [ ${stage} -le 9 ] && [ ${stop_stage} -ge 9 ]; then
echo "stage 9: Scoring finetuned models"
if [ ! -e dscore ]; then
--
Gitblit v1.9.1