Initial commit: FunASR Speech Recognition Toolkit

Add complete FunASR codebase including models, runtime, and documentation.

examples/aishell/conformer/local/aishell_data_prep.sh

@@ -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;

examples/aishell/conformer/local/download_and_untar.sh

@@ -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;