Merge pull request #4592 from brianyan918/egs2_aesrc

Egs2 aesrc

egs2/README.md

@@ -8,6 +8,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 
 | Directory name          | Corpus name                                                                                                                      | Task                    | Language              | URL                                                                                                          | Note         |
 |-------------------------|----------------------------------------------------------------------------------------------------------------------------------|-------------------------| --------------------- | ------------------------------------------------------------------------------------------------------------ | ------------ |
+| aesrc2020               | Accented English Speech Recognition Challenge 2020                                                                               | ASR                     | ENG                   | https://arxiv.org/abs/2102.10233                                                                             |              |
 | aidatatang_200zh        | Aidatatang_200zh A free Chinese Mandarin speech corpus                                                                           | ASR                     | CMN                   | http://www.openslr.org/resources/62                                                                          |              |
 | aishell                 | AISHELL-ASR0009-OS1 Open Source Mandarin Speech Corpus                                                                           | ASR                     | CMN                   | http://www.aishelltech.com/kysjcp                                                                            |              |
 | aishell2                | AISHELL-2 Open Source Mandarin Speech Corpus                                                                                     | ASR                     | CMN                   | https://www.aishelltech.com/aishell_2                                                                        |              |

egs2/aesrc2020/asr1/README.md

@@ -0,0 +1,34 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Sat Aug 20 06:55:57 EDT 2022`
+- python version: `3.8.13 (default, Mar 28 2022, 11:38:47)  [GCC 7.5.0]`
+- espnet version: `espnet 202207`
+- pytorch version: `pytorch 1.8.1`
+- Git hash: `c892feb2ba248c85b683bf3cdef6c8f7ce85449a`
+  - Commit date: `Thu Aug 18 11:54:56 2022 -0400`
+
+## asr_train_asr_raw_en_bpe5000_sp
+
+- Model link: [huggingface](https://huggingface.co/espnet/brianyan918_aesrc2020_asr_conformer)
+- ASR config: [./conf/train_asr.yaml](./conf/train_asr.yaml)
+- Inference config: [./conf/decode_asr.yaml](./conf/decode_asr.yaml)
+
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/test|15299|146813|94.8|4.7|0.6|0.7|5.9|31.9|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/test|15299|708064|97.9|1.2|0.9|0.7|2.8|31.9|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave/test|15299|165136|93.2|4.3|2.6|0.6|7.4|31.9|
+

egs2/aesrc2020/asr1/asr.sh

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

egs2/aesrc2020/asr1/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/aesrc2020/asr1/conf/decode_asr.yaml

@@ -0,0 +1,6 @@
+beam_size: 20
+ctc_weight: 0.3
+lm_weight: 0.0
+maxlenratio: 0.0
+minlenratio: 0.0
+penalty: 0.0

egs2/aesrc2020/asr1/conf/fbank.conf

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

egs2/aesrc2020/asr1/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/aesrc2020/asr1/conf/pitch.conf

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

egs2/aesrc2020/asr1/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/aesrc2020/asr1/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/aesrc2020/asr1/conf/train_asr.yaml

@@ -0,0 +1 @@
+tuning/train_asr_conformer_lr2e-3_warmup15k_amp_nondeterministic.yaml

egs2/aesrc2020/asr1/conf/tuning/train_asr_conformer_lr2e-3_warmup15k_amp_nondeterministic.yaml

@@ -0,0 +1,84 @@
+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
+
+frontend_conf:
+    n_fft: 512
+    win_length: 400
+    hop_length: 160
+
+seed: 2022
+log_interval: 400   
+num_att_plot: 0     
+num_workers: 4      
+sort_in_batch: descending       # how to sort data in making batch
+sort_batch: descending          # how to sort created batches
+batch_type: numel
+batch_bins: 16000000
+accum_grad: 4
+max_epoch: 70
+patience: none
+init: none
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+
+use_amp: true      
+cudnn_deterministic: false  
+cudnn_benchmark: false      
+
+optim: adam
+optim_conf:
+    lr: 0.002
+    weight_decay: 0.000001
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 15000
+
+specaug: specaug
+specaug_conf:
+    apply_time_warp: true
+    time_warp_window: 5
+    time_warp_mode: bicubic
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 27
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_ratio_range:
+    - 0.
+    - 0.05
+    num_time_mask: 5

egs2/aesrc2020/asr1/db.sh

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

egs2/aesrc2020/asr1/local/create_subsets.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+. ./path.sh || exit 1;
+. ./cmd.sh || exit 1;
+
+data=$1     # data transformed into kaldi format
+recog_set=$2
+
+ # divide development set for cross validation
+ if [ -d ${data} ];then
+     for i in ${recog_set};do
+         ./utils/subset_data_dir.sh --spk-list local/files/cvlist/${i}_cv_spk $data/data_all $data/cv/$i
+         cat $data/cv/$i/wav.scp >> $data/cv.scp
+     done
+     ./utils/filter_scp.pl --exclude $data/cv.scp $data/data_all/wav.scp > $data/train_and_dev.scp
+     #95-5 split for dev set
+     sed -n '0~20p' $data/train_and_dev.scp > $data/dev.scp
+     ./utils/filter_scp.pl --exclude $data/dev.scp $data/train_and_dev.scp > $data/train.scp
+     ./utils/subset_data_dir.sh --utt-list $data/train.scp $data/data_all $data/train
+     ./utils/subset_data_dir.sh --utt-list $data/dev.scp $data/data_all $data/valid
+     ./utils/subset_data_dir.sh --utt-list $data/cv.scp $data/data_all $data/test
+ fi
+
+echo "local/subset_data.sh succeeded"

egs2/aesrc2020/asr1/local/data.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env 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
+
+stage=1
+stop_stage=100000
+
+recog_set="US UK IND CHN JPN PT RU KR CA ES"
+
+log "$0 $*"
+. utils/parse_options.sh
+
+. ./db.sh
+. ./path.sh
+. ./cmd.sh
+
+
+if [ $# -ne 0 ]; then
+    log "Error: No positional arguments are required."
+    exit 2
+fi
+
+if [ -z "${AESRC2020}" ]; then
+    log "Fill the value of 'AESRC2020' of db.sh"    # place datatang.zip in this dir
+    exit 1
+fi
+
+if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
+    if [ ! -d "${AESRC2020}/Datatang-English/data" ]; then
+        echo "Data Download to ${AESRC2020}"
+        if [ ! -f "${AESRC2020}/datatang.zip" ]; then
+            echo "The AESRC2020 data needs to be requested via services@datatang.com"
+            exit 1
+        fi
+        local/download_and_untar.sh ${AESRC2020}/datatang.zip ${AESRC2020}
+    else
+        log "stage 1: ${AESRC2020}/Datatang-English/data is already existing. Skip data downloading"
+    fi
+fi
+
+if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
+    echo "Data preparation"
+    local/data_prep.sh ${AESRC2020}/Datatang-English/data data
+    ./utils/fix_data_dir.sh data/data_all
+    local/create_subsets.sh data "${recog_set}"
+fi
+
+log "Successfully finished. [elapsed=${SECONDS}s]"