Merge pull request #4183 from AshibaWu/mediaspeech-asr

Add MediaSpeech ASR recipe

egs/commonvoice/asr1/local/download_and_untar.sh

@@ -16,7 +16,7 @@ fi
 
 if [ $# -ne 3 ]; then
   echo "Usage: $0 [--remove-archive] <data-base> <url> <filename>"
-  echo "e.g.: $0 /export/data/ https://common-voice-data-download.s3.amazonaws.com/cv_corpus_v1.tar.gz cv_corpus_v1.tar.gz"
+  echo "e.g.: $0 /export/data/ https://us.openslr.org/resources/108/FR.tgz"
   echo "With --remove-archive it will remove the archive after successfully un-tarring it."
   exit 0;
 fi

egs2/README.md

@@ -62,6 +62,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | ljspeech                | The LJ Speech Dataset                                                                                                            | TTS                     | ENG                  | https://keithito.com/LJ-Speech-Dataset/                                                                      |              |
 | 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                                                  |              |
+| 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/                                                                  |              |
 | mini_librispeech        | Mini version of Librispeech corpus                                                                                               | DIAR                    | ENG                  | https://openslr.org/31/                                                                                      |              |

egs2/TEMPLATE/asr1/db.sh

@@ -46,6 +46,7 @@ LIBRILIGHT_LIMITED=
 FSC=
 SLURP=
 VOXCELEB=
+MEDIASPEECH=downloads
 MINI_LIBRISPEECH=downloads
 MISP2021=
 LIBRIMIX=downloads
@@ -217,6 +218,7 @@ if [[ "$(hostname -d)" == clsp.jhu.edu ]]; then
     FSC=
     SNIPS= # smart-light-en-closed-field data path
     SLURP=
+    MEDIASPEECH=downloads
     MINI_LIBRISPEECH=downloads
     LIBRITTS=
     LJSPEECH=downloads

egs2/mediaspeech/asr1/README.md

@@ -0,0 +1,34 @@
+# Hugging Face
+Model is available in Hugging Face: https://huggingface.co/espnet/mediaspeech-fr-hubert
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Tue Mar 22 13:50:31 UTC 2022`
+- python version: `3.7.11 (default, Jul 27 2021, 14:32:16)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.7a1`
+- pytorch version: `pytorch 1.10.1`
+- Git hash: `1991a25855821b8b61d775681aa0cdfd6161bbc8`
+  - Commit date: `Mon Mar 21 22:19:19 2022 +0800`
+
+## asr_train_asr_hubert_raw_as_bpe150_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave/dev_as|249|10072|49.7|41.2|9.1|7.0|57.2|100.0|
+|inference_asr_model_valid.acc.ave/test_as|249|9920|51.1|40.1|8.9|6.5|55.4|100.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave/dev_as|249|58679|80.9|8.0|11.1|7.2|26.3|100.0|
+|inference_asr_model_valid.acc.ave/test_as|249|58694|82.1|7.2|10.8|7.1|25.0|100.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave/dev_as|249|30837|69.5|19.0|11.5|6.3|36.8|100.0|
+|inference_asr_model_valid.acc.ave/test_as|249|30942|70.7|17.9|11.4|6.0|35.3|100.0|

egs2/mediaspeech/asr1/asr.sh

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

egs2/mediaspeech/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/mediaspeech/asr1/conf/decode_asr.yaml

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

egs2/mediaspeech/asr1/conf/fbank.conf

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

egs2/mediaspeech/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/mediaspeech/asr1/conf/pitch.conf

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

egs2/mediaspeech/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/mediaspeech/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/mediaspeech/asr1/conf/train_asr.yaml

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

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

@@ -0,0 +1,70 @@
+cudnn_benchmark: false 
+cudnn_deterministic: false 
+use_amp: true 
+encoder: conformer
+encoder_conf:
+    output_size: 512
+    attention_heads: 8
+    linear_units: 2048
+    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
+    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: 8
+    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
+
+optim: adam
+optim_conf:
+    lr: 0.0002
+scheduler: warmuplr     # pytorch v1.1.0+ required #Tune warmup steps
+scheduler_conf:
+    warmup_steps: 25000
+max_epoch: 50
+
+frontend_conf:
+  n_fft: 512
+  hop_length: 256
+
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+    extract_feats_in_collect_stats: false   # Note: "False" means during collect stats (stage 10), generating dummy stats files rather than extract_feats by forward frontend.
+
+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
+
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10