Skip to content

Commit

Permalink
aishell example
Browse files Browse the repository at this point in the history
  • Loading branch information
LauraGPT committed Feb 19, 2024
1 parent d92cd5a commit 1448e02
Show file tree
Hide file tree
Showing 29 changed files with 2,454 additions and 88 deletions.
2 changes: 2 additions & 0 deletions data/list/text.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
ID0012W0013 当客户风险承受能力评估依据发生变化时
ID0012W0014 杨涛不得不将工厂关掉
2 changes: 2 additions & 0 deletions data/list/wav.scp
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
ID0012W0013 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0013.wav
ID0012W0014 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0014.wav
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@

# network architecture
model: funasr.cli.models.paraformer:Paraformer
model: Paraformer
model_conf:
ctc_weight: 0.3
lsm_weight: 0.1
Expand All @@ -9,9 +9,8 @@ model_conf:
sampling_ratio: 0.4
use_1st_decoder_loss: true


# encoder related
encoder: conformer
# encoder
encoder: ConformerEncoder
encoder_conf:
output_size: 256 # dimension of attention
attention_heads: 4
Expand All @@ -29,8 +28,8 @@ encoder_conf:
use_cnn_module: true
cnn_module_kernel: 15

# decoder related
decoder: paraformer_decoder_san
# decoder
decoder: ParaformerSANDecoder
decoder_conf:
attention_heads: 4
linear_units: 2048
Expand All @@ -40,8 +39,17 @@ decoder_conf:
self_attention_dropout_rate: 0.0
src_attention_dropout_rate: 0.0

# predictor
predictor: CifPredictor
predictor_conf:
idim: 256
threshold: 1.0
l_order: 1
r_order: 1
tail_threshold: 0.45

# frontend related
frontend: wav_frontend
frontend: WavFrontend
frontend_conf:
fs: 16000
window: hamming
Expand All @@ -51,29 +59,7 @@ frontend_conf:
lfr_m: 1
lfr_n: 1


train_conf:
accum_grad: 1
grad_clip: 5
max_epoch: 150
val_scheduler_criterion:
- valid
- acc
best_model_criterion:
- - valid
- acc
- max
keep_nbest_models: 10
log_interval: 50

optim: adam
optim_conf:
lr: 0.0005
scheduler: warmuplr
scheduler_conf:
warmup_steps: 30000

specaug: specaug
specaug: SpecAug
specaug_conf:
apply_time_warp: true
time_warp_window: 5
Expand All @@ -89,25 +75,43 @@ specaug_conf:
- 40
num_time_mask: 2

predictor: cif_predictor
predictor_conf:
idim: 256
threshold: 1.0
l_order: 1
r_order: 1
tail_threshold: 0.45
train_conf:
accum_grad: 1
grad_clip: 5
max_epoch: 150
keep_nbest_models: 10
avg_nbest_model: 5
log_interval: 50

optim: adam
optim_conf:
lr: 0.0005
scheduler: warmuplr
scheduler_conf:
warmup_steps: 30000

dataset: AudioDataset
dataset_conf:
data_names: speech,text
data_types: sound,text
index_ds: IndexDSJsonl
batch_sampler: RankFullLocalShuffleBatchSampler
batch_type: example # example or length
batch_size: 32 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
buffer_size: 1024
shuffle: True
shuffle_conf:
shuffle_size: 2048
sort_size: 500
batch_conf:
batch_type: example
batch_size: 2
num_workers: 8
num_workers: 0

tokenizer: CharTokenizer
tokenizer_conf:
unk_symbol: <unk>
split_with_space: true


ctc_conf:
dropout_rate: 0.0
ctc_type: builtin
reduce: true
ignore_nan_grad: true
normalize: null


normalize: null
9 changes: 9 additions & 0 deletions examples/aishell/finetune.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@

cmd="funasr/bin/train.py"

python $cmd \
--config-path "/Users/zhifu/funasr_github/test_local/funasr_cli_egs" \
--config-name "config.yaml" \
++token_list="/Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt" \
++train_data_set_list="/Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl" \
++output_dir="/nfs/zhifu.gzf/ckpt/funasr2/exp1"
66 changes: 66 additions & 0 deletions examples/aishell/paraformer/local/aishell_data_prep.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
#!/bin/bash

# Copyright 2017 Xingyu Na
# Apache 2.0

#. ./path.sh || exit 1;

if [ $# != 3 ]; then
echo "Usage: $0 <audio-path> <text-path> <output-path>"
echo " $0 /export/a05/xna/data/data_aishell/wav /export/a05/xna/data/data_aishell/transcript data"
exit 1;
fi

aishell_audio_dir=$1
aishell_text=$2/aishell_transcript_v0.8.txt
output_dir=$3

train_dir=$output_dir/data/local/train
dev_dir=$output_dir/data/local/dev
test_dir=$output_dir/data/local/test
tmp_dir=$output_dir/data/local/tmp

mkdir -p $train_dir
mkdir -p $dev_dir
mkdir -p $test_dir
mkdir -p $tmp_dir

# data directory check
if [ ! -d $aishell_audio_dir ] || [ ! -f $aishell_text ]; then
echo "Error: $0 requires two directory arguments"
exit 1;
fi

# find wav audio file for train, dev and test resp.
find $aishell_audio_dir -iname "*.wav" > $tmp_dir/wav.flist
n=`cat $tmp_dir/wav.flist | wc -l`
[ $n -ne 141925 ] && \
echo Warning: expected 141925 data data files, found $n

grep -i "wav/train" $tmp_dir/wav.flist > $train_dir/wav.flist || exit 1;
grep -i "wav/dev" $tmp_dir/wav.flist > $dev_dir/wav.flist || exit 1;
grep -i "wav/test" $tmp_dir/wav.flist > $test_dir/wav.flist || exit 1;

rm -r $tmp_dir

# Transcriptions preparation
for dir in $train_dir $dev_dir $test_dir; do
echo Preparing $dir transcriptions
sed -e 's/\.wav//' $dir/wav.flist | awk -F '/' '{print $NF}' > $dir/utt.list
paste -d' ' $dir/utt.list $dir/wav.flist > $dir/wav.scp_all
utils/filter_scp.pl -f 1 $dir/utt.list $aishell_text > $dir/transcripts.txt
awk '{print $1}' $dir/transcripts.txt > $dir/utt.list
utils/filter_scp.pl -f 1 $dir/utt.list $dir/wav.scp_all | sort -u > $dir/wav.scp
sort -u $dir/transcripts.txt > $dir/text
done

mkdir -p $output_dir/data/train $output_dir/data/dev $output_dir/data/test

for f in wav.scp text; do
cp $train_dir/$f $output_dir/data/train/$f || exit 1;
cp $dev_dir/$f $output_dir/data/dev/$f || exit 1;
cp $test_dir/$f $output_dir/data/test/$f || exit 1;
done

echo "$0: AISHELL data preparation succeeded"
exit 0;
105 changes: 105 additions & 0 deletions examples/aishell/paraformer/local/download_and_untar.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,105 @@
#!/usr/bin/env bash

# Copyright 2014 Johns Hopkins University (author: Daniel Povey)
# 2017 Xingyu Na
# Apache 2.0

remove_archive=false

if [ "$1" == --remove-archive ]; then
remove_archive=true
shift
fi

if [ $# -ne 3 ]; then
echo "Usage: $0 [--remove-archive] <data-base> <url-base> <corpus-part>"
echo "e.g.: $0 /export/a05/xna/data www.openslr.org/resources/33 data_aishell"
echo "With --remove-archive it will remove the archive after successfully un-tarring it."
echo "<corpus-part> can be one of: data_aishell, resource_aishell."
fi

data=$1
url=$2
part=$3

if [ ! -d "$data" ]; then
echo "$0: no such directory $data"
exit 1;
fi

part_ok=false
list="data_aishell resource_aishell"
for x in $list; do
if [ "$part" == $x ]; then part_ok=true; fi
done
if ! $part_ok; then
echo "$0: expected <corpus-part> to be one of $list, but got '$part'"
exit 1;
fi

if [ -z "$url" ]; then
echo "$0: empty URL base."
exit 1;
fi

if [ -f $data/$part/.complete ]; then
echo "$0: data part $part was already successfully extracted, nothing to do."
exit 0;
fi

# sizes of the archive files in bytes.
sizes="15582913665 1246920"

if [ -f $data/$part.tgz ]; then
size=$(/bin/ls -l $data/$part.tgz | awk '{print $5}')
size_ok=false
for s in $sizes; do if [ $s == $size ]; then size_ok=true; fi; done
if ! $size_ok; then
echo "$0: removing existing file $data/$part.tgz because its size in bytes $size"
echo "does not equal the size of one of the archives."
rm $data/$part.tgz
else
echo "$data/$part.tgz exists and appears to be complete."
fi
fi

if [ ! -f $data/$part.tgz ]; then
if ! command -v wget >/dev/null; then
echo "$0: wget is not installed."
exit 1;
fi
full_url=$url/$part.tgz
echo "$0: downloading data from $full_url. This may take some time, please be patient."

cd $data || exit 1
if ! wget --no-check-certificate $full_url; then
echo "$0: error executing wget $full_url"
exit 1;
fi
fi

cd $data || exit 1

if ! tar -xvzf $part.tgz; then
echo "$0: error un-tarring archive $data/$part.tgz"
exit 1;
fi

touch $data/$part/.complete

if [ $part == "data_aishell" ]; then
cd $data/$part/wav || exit 1
for wav in ./*.tar.gz; do
echo "Extracting wav from $wav"
tar -zxf $wav && rm $wav
done
fi

echo "$0: Successfully downloaded and un-tarred $data/$part.tgz"

if $remove_archive; then
echo "$0: removing $data/$part.tgz file since --remove-archive option was supplied."
rm $data/$part.tgz
fi

exit 0;
Loading

0 comments on commit 1448e02

Please sign in to comment.