Merge pull request #4635 from tjysdsg/magicdata_mandarin_read_speech

egs2/README.md

@@ -70,6 +70,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | lrs3                    | The Oxford-BBC Lip Reading Sentences 3 (LRS3) Dataset                                                                            | ASR                     | ENG                  | https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrs3.html                                                  |              |
 | lrs2                    | The Oxford-BBC Lip Reading Sentences 2 (LRS2) Dataset                                                                            | Lipreading/ASR          | ENG                  | https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrs2.html                                                  |              |
 | lt_slurp_spatialized                    | Spatialized Libri-Trans and Spatialized SLURP (LT-S and SLURP-S), Enhancement for Translation and Understanding Dataset                                   | SE/ST/SLU          | ENG                  |                                                   |              |
+| magicdata               | MAGICDATA Mandarin Chinese Read Speech Corpus                                                                                    | ASR                     | ENG                  | https://www.openslr.org/68/                                                                                  |              |
 | mediaspeech             | MediaSpeech: Multilanguage ASR Benchmark and Dataset                                    | ASR                     | FRA                  | https://www.openslr.org/108/                                                                           |              |
 | microsoft_speech        | Microsoft Speech Corpus (Indian languages)                                                                                       | ASR                     | 3 languages          | https://msropendata.com/datasets/7230b4b1-912d-400e-be58-f84e0512985e                                        |              |
 | mini_an4                | Mini version of CMU AN4 database for the integration test                                                                        | ASR/TTS/SE              | ENG                  | http://www.speech.cs.cmu.edu/databases/an4/                                                                  |              |

egs2/TEMPLATE/asr1/db.sh

@@ -51,6 +51,7 @@ SLURP=
 SLURP_S= # Output file path
 LIBRITRANS_S= # Output file path
 VOXCELEB=
+MAGICDATA=downloads
 MEDIASPEECH=downloads
 MINI_LIBRISPEECH=downloads
 MISP2021=
@@ -300,4 +301,4 @@ if [[ "$(hostname -d)" == clsp.jhu.edu ]]; then
     GOOGLEI18N=downloads
     MALAYALAM=
 
-fi
+fi

egs2/magicdata/asr1/README.md

@@ -0,0 +1,19 @@
+# RESULTS
+
+## Environments
+
+- date: `Wed Sep 21 01:11:58 EDT 2022`
+- python version: `3.9.12 (main, Apr  5 2022, 06:56:58)  [GCC 7.5.0]`
+- espnet version: `espnet 202207`
+- pytorch version: `pytorch 1.8.1+cu102`
+- Git hash: `9d0f3b3e1be6650d38cc5008518f445308fe06d9`
+    - Commit date: `Mon Sep 19 20:27:41 2022 -0400`
+- Pretrained model: https://huggingface.co/espnet/jiyangtang_magicdata_asr_conformer_lm_transformer
+
+## [Conformer](conf/tuning/train_asr_conformer.yaml) with [Transformer-LM](conf/tuning/train_lm_transformer.yaml)
+
+### CER
+
+| dataset                                                                                       | Snt   | Wrd    | Corr | Sub | Del | Ins | Err | S.Err |
+|-----------------------------------------------------------------------------------------------|-------|--------|------|-----|-----|-----|-----|-------|
+| decode_asr_rnn_lm_lm_train_lm_transformer_zh_char_valid.loss.ave_asr_model_valid.acc.ave/test | 24279 | 243325 | 96.4 | 1.7 | 2.0 | 0.1 | 3.7 | 15.6  |

egs2/magicdata/asr1/asr.sh

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

egs2/magicdata/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/magicdata/asr1/conf/decode_asr_rnn.yaml

@@ -0,0 +1 @@
+tuning/decode_asr_rnn.yaml

egs2/magicdata/asr1/conf/fbank.conf

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

egs2/magicdata/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/magicdata/asr1/conf/pitch.conf

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

egs2/magicdata/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/magicdata/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/magicdata/asr1/conf/train_asr.yaml

@@ -0,0 +1 @@
+tuning/train_asr_conformer.yaml

egs2/magicdata/asr1/conf/train_lm_transformer.yaml

@@ -0,0 +1 @@
+tuning/train_lm_transformer.yaml

egs2/magicdata/asr1/conf/tuning/decode_asr_rnn.yaml

@@ -0,0 +1,6 @@
+beam_size: 20
+penalty: 0.0
+maxlenratio: 0.0
+minlenratio: 0.0
+ctc_weight: 0.6
+lm_weight: 0.3

egs2/magicdata/asr1/conf/tuning/train_asr_conformer.yaml

@@ -0,0 +1,77 @@
+# network architecture
+# encoder related
+encoder: conformer
+encoder_conf:
+    output_size: 512    # dimension of attention
+    attention_heads: 8
+    linear_units: 2048  # the number of units of position-wise feed forward
+    num_blocks: 12      # the number of encoder blocks
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d # encoder architecture type
+    normalize_before: true
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    macaron_style: true
+    use_cnn_module: true
+    cnn_module_kernel: 31
+
+# decoder related
+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: 0.0
+    src_attention_dropout_rate: 0.0
+
+# hybrid CTC/attention
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1     # label smoothing option
+    length_normalized_loss: false
+
+# minibatch related
+batch_type: numel
+batch_bins: 20000000
+num_workers: 4
+
+# optimization related
+accum_grad: 4
+grad_clip: 5
+max_epoch: 50
+val_scheduler_criterion:
+    - valid
+    - acc
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+
+optim: adam
+optim_conf:
+   lr: 0.0005
+scheduler: warmuplr
+scheduler_conf:
+   warmup_steps: 30000
+
+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
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2

egs2/magicdata/asr1/conf/tuning/train_lm_transformer.yaml

@@ -0,0 +1,29 @@
+lm: transformer
+lm_conf:
+    pos_enc: null
+    embed_unit: 128
+    att_unit: 512
+    head: 8
+    unit: 2048
+    layer: 16
+    dropout_rate: 0.1
+
+# optimization related
+grad_clip: 5.0
+batch_type: numel
+batch_bins: 2000000
+accum_grad: 1
+max_epoch: 15  # 15epoch is enougth
+
+optim: adam
+optim_conf:
+   lr: 0.001
+scheduler: warmuplr
+scheduler_conf:
+   warmup_steps: 25000
+
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 10  # 10 is good.

egs2/magicdata/asr1/db.sh

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