Merge pull request espnet#4134 from YushiUeda/swbd_sentiment

ESPnet2 swbd_sentiment recipe

egs2/README.md

@@ -75,6 +75,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | su_openslr36            | Sundanese                                                                               | ASR                     | SUN                  | http://www.openslr.org/36                                                                                    |              |
 | swbd                    | Switchboard Corpus for 2-channel Conversational Telephone Speech (300h)                 | ASR                     | ENG                  | https://catalog.ldc.upenn.edu/LDC97S62                                                                       |              |
 | swbd_da                 | NXT Switchboard Annotations                                                             | SLU                     | ENG                  | https://catalog.ldc.upenn.edu/LDC2009T26                                                                     |              |
+| swbd_sentiment          | Speech Sentiment Annotations                                                            | SLU                     | ENG                  | https://catalog.ldc.upenn.edu/LDC2020T14                                                                    |              |
 | tedlium2                | TED-LIUM corpus release 2                                                               | ASR                     | ENG                  | https://www.openslr.org/19/, http://www.lrec-conf.org/proceedings/lrec2014/pdf/1104_Paper.pdf                |              |
 | thchs30                 | A Free Chinese Speech Corpus Released by CSLT@Tsinghua University                       | TTS                     | CMN                  | https://www.openslr.org/18/                                                                                  |              |
 | timit                   | TIMIT Acoustic-Phonetic Continuous Speech Corpus                                        | ASR                     | ENG                  | https://catalog.ldc.upenn.edu/LDC93S1                                                                        |              |

egs2/swbd_sentiment/asr1/README.md

@@ -0,0 +1,35 @@
+# RESULTS
+## Dataset
+- Speech Sentiment Annotations (Switchboard Sentiment)
+   - Data: https://catalog.ldc.upenn.edu/LDC2020T14
+   - Paper: https://catalog.ldc.upenn.edu/docs/LDC2020T14/LREC_2020_Switchboard_Senti.pdf
+
+## Environments
+- date: `Thu Mar  3 21:34:18 EST 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 1.9.0+cu102`
+- Git hash: `3b53aedc654fd30a828689c2139a1e130adac077`
+  - Commit date: `Fri Feb 25 00:13:16 2022 -0500`
+
+## Using Conformer based encoder and Transformer based decoder with spectral augmentation and predicting transcript along with sentiment
+- ASR config: [conf/tuning/train_asr_conformer.yaml](conf/tuning/train_asr_conformer.yaml)
+- token_type: word
+- labels: Positive, Neutral, Negative
+- Pre-trained Model: https://huggingface.co/espnet/YushiUeda_swbd_sentiment_asr_train_asr_conformer
+
+|dataset|Snt|Intent Classification Macro F1 (%)| Weighted F1 (%)| Micro F1 (%)|
+|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave_10best/valid|2415|61.0|65.0|65.6|
+|decode_asr_asr_model_valid.acc.ave_10best/test|2438|61.4|64.4|64.6|
+
+## Using Conformer based encoder, Transformer based decoder and self-supervised learning features (Wav2vec2.0) with spectral augmentation and predicting transcript along with sentiment
+- ASR config: [conf/tuning/train_asr_conformer_wav2vec2.yaml](conf/tuning/train_asr_conformer_wav2vec2.yaml)
+- token_type: word
+- labels: Positive, Neutral, Negative
+- Pre-trained Model: https://huggingface.co/espnet/YushiUeda_swbd_sentiment_asr_train_asr_conformer_wav2vec2
+
+|dataset|Snt|Intent Classification Macro F1 (%)| Weighted F1 (%)| Micro F1 (%)|
+|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.ave_10best/valid|2415|64.5|67.5|67.4|
+|decode_asr_asr_model_valid.acc.ave_10best/test|2438|64.1|66.5|66.3|

egs2/swbd_sentiment/asr1/asr.sh

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

egs2/swbd_sentiment/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/swbd_sentiment/asr1/conf/decode_asr.yaml

@@ -0,0 +1 @@
+beam_size: 1

egs2/swbd_sentiment/asr1/conf/fbank.conf

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

egs2/swbd_sentiment/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/swbd_sentiment/asr1/conf/pitch.conf

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

egs2/swbd_sentiment/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/swbd_sentiment/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/swbd_sentiment/asr1/conf/train_asr.yaml

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

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

@@ -0,0 +1,62 @@
+# network architecture
+# encoder related
+encoder: conformer
+encoder_conf:
+    output_size: 512
+    attention_heads: 4
+    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 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: 0.1
+    src_attention_dropout_rate: 0.1
+
+optim: adam
+optim_conf:
+    lr: 0.0025
+scheduler: warmuplr     # pytorch v1.1.0+ required
+scheduler_conf:
+    warmup_steps: 40000
+batch_type: numel
+batch_bins: 40000000
+accum_grad: 3
+max_epoch: 50
+
+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

egs2/swbd_sentiment/asr1/conf/tuning/train_asr_conformer_wav2vec2.yaml

@@ -0,0 +1,90 @@
+# network architecture
+# encoder related
+
+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: 0.0025
+scheduler: warmuplr   # pytorch v1.1.0+ required #Tune warmup steps
+scheduler_conf:
+  warmup_steps: 25000
+batch_type: numel
+batch_bins: 40000000
+accum_grad: 3
+max_epoch: 50
+
+freeze_param: [
+"frontend.upstream"
+]
+
+frontend_conf:
+ n_fft: 512
+ hop_length: 256
+
+frontend: s3prl
+frontend_conf:
+  frontend_conf:
+    upstream: wav2vec2_large_ll60k # Note: If the upstream is changed, please change the input_size in the preencoder.
+    # If using hubert, change the above line to "upstream: hubert_large_ll60k"
+  download_dir: ./hub
+  multilayer_feature: True
+
+preencoder: linear
+preencoder_conf:
+  input_size: 1024 # Note: If the upstream is changed, please change this value accordingly.
+  output_size: 80
+
+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

egs2/swbd_sentiment/asr1/db.sh

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

egs2/swbd_sentiment/asr1/local/MSU_single_letter.txt

@@ -0,0 +1 @@
+../../../../egs/swbd/asr1/local/MSU_single_letter.txt