Add recipe for OCR task on IAM handwriting dataset

egs2/README.md

@@ -55,6 +55,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | how2_2000h              | How2_2000h fbank features                                                                                                        | ASR/SUM                 | ENG->POR              | https://arxiv.org/pdf/2110.06263.pdf                                                                         |              |
 | hub4_spanish            | 1997 Spanish Broadcase News Speech                                                                                               | ASR                     | SPA                   | https://catalog.ldc.upenn.edu/LDC98S74                                                                       |              |
 | hui_acg                 | HUI-audio-corpus-german                                                                                                          | TTS                     | DEU                   | https://opendata.iisys.de/datasets.html#hui-audio-corpus-german                                              |              |
+| iam                     | IAM Handwriting Database 3.0                                                                                                     | OCR                     | ENG                   | https://fki.tic.heia-fr.ch/databases/iam-handwriting-database                                                |              |
 | iemocap                 | IEMOCAP database: The Interactive Emotional Dyadic Motion Capture database                                                       | SLU                     | ENG                   | https://sail.usc.edu/iemocap/                                                                                |              |
 | indic_speech            | IndicSpeech: Text-to-Speech Corpus for Indian Languages                                                                          | TTS                     | 3 indic languages    | http://cvit.iiit.ac.in/research/projects/cvit-projects/text-to-speech-dataset-for-indian-languages            |              |
 | iwslt14                 | IWSLT14 MT shared task                                                                                                           | MT                      | DEU->ENG             | http://dl.fbaipublicfiles.com/fairseq/data/iwslt14/de-en.tgz                                                  |              |

egs2/TEMPLATE/asr1/asr.sh

@@ -552,7 +552,7 @@ if ! "${skip_data_prep}"; then
                     _suf=""
                 fi
                 # Generate dummy wav.scp to avoid error by copy_data_dir.sh
-                <data/"${dset}"/cmvn.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
+                <data/"${dset}"/feats.scp awk ' { print($1,"<DUMMY>") }' > data/"${dset}"/wav.scp
                 utils/copy_data_dir.sh --validate_opts --non-print data/"${dset}" "${data_feats}${_suf}/${dset}"
 
                 # Derive the the frame length and feature dimension

egs2/TEMPLATE/asr1/db.sh

@@ -158,6 +158,7 @@ HARPERVALLEY=downloads
 TALROMUR=downloads
 DCASE=
 TEDX_SPANISH=downloads
+IAM=downloads
 OFUTON=
 OPENCPOP=
 M_AILABS=downloads

egs2/iam/ocr1/README.md

@@ -0,0 +1,36 @@
+This is a recipe for the IAM handwriting recognition dataset, and is an experiment with using end-to-end
+ASR models to solve an OCR task.
+
+To run, first make an account on https://fki.tic.heia-fr.ch/databases/iam-handwriting-database and fill
+in the username and password in `local/data.sh`. Then, run `./run.sh`
+
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Fri Oct  7 05:52:11 EDT 2022`
+- python version: `3.7.13 (default, Mar 29 2022, 02:18:16)  [GCC 7.5.0]`
+- espnet version: `espnet 202207`
+- pytorch version: `pytorch 1.10.0`
+- Git hash: `5a6319300231b8193f1b6e8465d572be63150119`
+  - Commit date: `Sat Sep 24 12:14:08 2022 -0400`
+
+## asr_conformer_full_vocab
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave/test|2915|25932|80.3|17.4|2.3|0.9|20.6|73.4|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave/test|2915|125616|93.9|4.4|1.8|0.7|6.8|73.4|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave/test|2915|128531|94.0|4.3|1.7|0.7|6.7|73.4|
+

egs2/iam/ocr1/asr.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/asr.sh

egs2/iam/ocr1/cmd.sh

@@ -0,0 +1,110 @@
+# ====== About run.pl, queue.pl, slurm.pl, and ssh.pl ======
+# Usage: <cmd>.pl [options] JOB=1:<nj> <log> <command...>
+# e.g.
+#   run.pl --mem 4G JOB=1:10 echo.JOB.log echo JOB
+#
+# Options:
+#   --time <time>: Limit the maximum time to execute.
+#   --mem <mem>: Limit the maximum memory usage.
+#   -–max-jobs-run <njob>: Limit the number parallel jobs. This is ignored for non-array jobs.
+#   --num-threads <ngpu>: Specify the number of CPU core.
+#   --gpu <ngpu>: Specify the number of GPU devices.
+#   --config: Change the configuration file from default.
+#
+# "JOB=1:10" is used for "array jobs" and it can control the number of parallel jobs.
+# The left string of "=", i.e. "JOB", is replaced by <N>(Nth job) in the command and the log file name,
+# e.g. "echo JOB" is changed to "echo 3" for the 3rd job and "echo 8" for 8th job respectively.
+# Note that the number must start with a positive number, so you can't use "JOB=0:10" for example.
+#
+# run.pl, queue.pl, slurm.pl, and ssh.pl have unified interface, not depending on its backend.
+# These options are mapping to specific options for each backend and
+# it is configured by "conf/queue.conf" and "conf/slurm.conf" by default.
+# If jobs failed, your configuration might be wrong for your environment.
+#
+#
+# The official documentation for run.pl, queue.pl, slurm.pl, and ssh.pl:
+#   "Parallelization in Kaldi": http://kaldi-asr.org/doc/queue.html
+# =========================================================~
+
+
+# Select the backend used by run.sh from "local", "stdout", "sge", "slurm", or "ssh"
+cmd_backend='local'
+
+# Local machine, without any Job scheduling system
+if [ "${cmd_backend}" = local ]; then
+
+    # The other usage
+    export train_cmd="run.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="run.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="run.pl"
+
+# Local machine logging to stdout and log file, without any Job scheduling system
+elif [ "${cmd_backend}" = stdout ]; then
+
+    # The other usage
+    export train_cmd="stdout.pl"
+    # Used for "*_train.py": "--gpu" is appended optionally by run.sh
+    export cuda_cmd="stdout.pl"
+    # Used for "*_recog.py"
+    export decode_cmd="stdout.pl"
+
+
+# "qsub" (Sun Grid Engine, or derivation of it)
+elif [ "${cmd_backend}" = sge ]; then
+    # The default setting is written in conf/queue.conf.
+    # You must change "-q g.q" for the "queue" for your environment.
+    # To know the "queue" names, type "qhost -q"
+    # Note that to use "--gpu *", you have to setup "complex_value" for the system scheduler.
+
+    export train_cmd="queue.pl"
+    export cuda_cmd="queue.pl"
+    export decode_cmd="queue.pl"
+
+
+# "qsub" (Torque/PBS.)
+elif [ "${cmd_backend}" = pbs ]; then
+    # The default setting is written in conf/pbs.conf.
+
+    export train_cmd="pbs.pl"
+    export cuda_cmd="pbs.pl"
+    export decode_cmd="pbs.pl"
+
+
+# "sbatch" (Slurm)
+elif [ "${cmd_backend}" = slurm ]; then
+    # The default setting is written in conf/slurm.conf.
+    # You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
+    # To know the "partion" names, type "sinfo".
+    # You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
+    # The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
+
+    export train_cmd="slurm.pl"
+    export cuda_cmd="slurm.pl"
+    export decode_cmd="slurm.pl"
+
+elif [ "${cmd_backend}" = ssh ]; then
+    # You have to create ".queue/machines" to specify the host to execute jobs.
+    # e.g. .queue/machines
+    #   host1
+    #   host2
+    #   host3
+    # Assuming you can login them without any password, i.e. You have to set ssh keys.
+
+    export train_cmd="ssh.pl"
+    export cuda_cmd="ssh.pl"
+    export decode_cmd="ssh.pl"
+
+# This is an example of specifying several unique options in the JHU CLSP cluster setup.
+# Users can modify/add their own command options according to their cluster environments.
+elif [ "${cmd_backend}" = jhu ]; then
+
+    export train_cmd="queue.pl --mem 2G"
+    export cuda_cmd="queue-freegpu.pl --mem 2G --gpu 1 --config conf/queue.conf"
+    export decode_cmd="queue.pl --mem 4G"
+
+else
+    echo "$0: Error: Unknown cmd_backend=${cmd_backend}" 1>&2
+    return 1
+fi

egs2/iam/ocr1/conf/fbank.conf

@@ -0,0 +1,2 @@
+--sample-frequency=16000 
+--num-mel-bins=80

egs2/iam/ocr1/conf/pbs.conf

@@ -0,0 +1,11 @@
+# Default configuration
+command qsub -V -v PATH -S /bin/bash
+option name=* -N $0
+option mem=* -l mem=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -l ncpus=$0
+option num_threads=1  # Do not add anything to qsub_opts
+option num_nodes=* -l nodes=$0:ppn=1
+default gpu=0
+option gpu=0
+option gpu=* -l ngpus=$0

egs2/iam/ocr1/conf/pitch.conf

@@ -0,0 +1 @@
+--sample-frequency=16000

egs2/iam/ocr1/conf/queue.conf

@@ -0,0 +1,12 @@
+# Default configuration
+command qsub -v PATH -cwd -S /bin/bash -j y -l arch=*64*
+option name=* -N $0
+option mem=* -l mem_free=$0,ram_free=$0
+option mem=0          # Do not add anything to qsub_opts
+option num_threads=* -pe smp $0
+option num_threads=1  # Do not add anything to qsub_opts
+option max_jobs_run=* -tc $0
+option num_nodes=* -pe mpi $0  # You must set this PE as allocation_rule=1
+default gpu=0
+option gpu=0
+option gpu=* -l gpu=$0 -q g.q

egs2/iam/ocr1/conf/slurm.conf

@@ -0,0 +1,14 @@
+# Default configuration
+command sbatch --export=PATH
+option name=* --job-name $0
+option time=* --time $0
+option mem=* --mem-per-cpu $0
+option mem=0
+option num_threads=* --cpus-per-task $0
+option num_threads=1 --cpus-per-task 1
+option num_nodes=* --nodes $0
+default gpu=0
+option gpu=0 -p cpu
+option gpu=* -p gpu --gres=gpu:$0 -c $0  # Recommend allocating more CPU than, or equal to the number of GPU
+# note: the --max-jobs-run option is supported as a special case
+# by slurm.pl and you don't have to handle it in the config file.

egs2/iam/ocr1/conf/train_asr_conformer.yaml

@@ -0,0 +1,55 @@
+# This config is adapted from the Librispeech conformer model
+
+keep_nbest_models: 10
+encoder: conformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    normalize_before: true
+    macaron_style: true
+    rel_pos_type: latest
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_kernel: 31
+
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.1
+    src_attention_dropout_rate: 0.1
+
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+
+batch_type: folded
+batch_size: 64 
+accum_grad: 1
+max_epoch: 200
+patience: none
+init: xavier_uniform
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+
+optim: adam
+optim_conf:
+    lr: 0.002
+    weight_decay: 0.000001
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 15000

egs2/iam/ocr1/db.sh

@@ -0,0 +1 @@
+../../TEMPLATE/asr1/db.sh

egs2/iam/ocr1/local/data.sh

@@ -0,0 +1,48 @@
+#!/bin/bash
+# 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
+
+log() {
+    local fname=${BASH_SOURCE[1]##*/}
+    echo -e "$(date '+%Y-%m-%dT%H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+
+SECONDS=0
+
+. ./db.sh
+. ./path.sh
+. ./cmd.sh
+
+stage=1
+stop_stage=2
+
+# Fill in username/password from account on https://fki.tic.heia-fr.ch/register
+iam_username=""
+iam_password=""
+
+# Set parameters for the feature dimensions used during image extraction,
+# see data_prep.py for details
+feature_dim=100
+downsampling_factor=0.5
+
+data_dir=data/
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    log "Stage 1.1: Downloading the IAM Handwriting dataset with username ${iam_username} and password ${iam_password}"
+    mkdir -p ${IAM}
+    local/download_and_untar.sh ${IAM} ${iam_username} ${iam_password}
+fi
+
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    log "Stage 1.2: Data Preparation - generating text, utt2spk, spk2utt, and feats.scp for train/valid/test splits"
+    if [ -e ${data_dir} ]; then
+        echo "Error: directory ${data_dir} already exists, to re-generate please first remove it manually"
+        exit 1
+    fi
+    python local/data_prep.py --feature_dim ${feature_dim} --downsampling_factor ${downsampling_factor}
+fi
+
+log "Successfully finished. [elapsed=${SECONDS}s]"