forked from espnet/espnet
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' of github.com:espnet/espnet into dpclanddan
- Loading branch information
Showing
80 changed files
with
3,378 additions
and
519 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,4 @@ | ||
| batch: 0 | ||
| beam-size: 10 | ||
| search-type: default | ||
| score-norm: True |
50 changes: 50 additions & 0 deletions
50
egs/librispeech/asr1/conf/tuning/transducer/train_conformer-rnn_transducer.yaml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| # minibatch related | ||
| batch-size: 32 | ||
| maxlen-in: 512 | ||
| maxlen-out: 150 | ||
|
|
||
| # optimization related | ||
| criterion: loss | ||
| early-stop-criterion: "validation/main/loss" | ||
| sortagrad: 0 | ||
| opt: noam | ||
| noam-adim: 256 | ||
| transformer-lr: 1.0 | ||
| transformer-warmup-steps: 25000 | ||
| epochs: 100 | ||
| patience: 0 | ||
| accum-grad: 4 | ||
| grad-clip: 5.0 | ||
|
|
||
| # network architecture | ||
| ## general | ||
| custom-enc-positional-encoding-type: rel_pos | ||
| custom-enc-self-attn-type: rel_self_attn | ||
| custom-enc-pw-activation-type: swish | ||
| ## encoder related | ||
| etype: custom | ||
| custom-enc-input-layer: vgg2l | ||
| enc-block-arch: | ||
| - type: conformer | ||
| d_hidden: 512 | ||
| d_ff: 2048 | ||
| heads: 4 | ||
| macaron_style: True | ||
| use_conv_mod: True | ||
| conv_mod_kernel: 15 | ||
| dropout-rate: 0.3 | ||
| att-dropout-rate: 0.3 | ||
| enc-block-repeat: 12 | ||
| ## decoder related | ||
| dtype: lstm | ||
| dlayers: 1 | ||
| dec-embed-dim: 1024 | ||
| dunits: 512 | ||
| dropout-rate-embed-decoder: 0.2 | ||
| dropout-rate-decoder: 0.1 | ||
| ## joint network related | ||
| joint-dim: 512 | ||
|
|
||
| # transducer related | ||
| model-module: "espnet.nets.pytorch_backend.e2e_asr_transducer:E2E" | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,39 @@ | ||
| ## pretrain_Train_pytorch_train_specaug | ||
|
|
||
| * Model files (archived to model.tar.gz by <code>$ pack_model.sh</code>) | ||
| - download link: <code>https://drive.google.com/file/d/1YUePEjk2Utgznr7sP0x4KdKCcPjbMM7C/view?usp=sharing</code> | ||
| - training config file: <code>conf/train.yaml</code> | ||
| - decoding config file: <code>conf/decode.yaml</code> | ||
| - preprocess config file: <code>conf/specaug.yaml</code> | ||
| - lm config file: <code>conf/lm.yaml</code> | ||
| - cmvn file: <code>data/pretrain_Train/cmvn.ark</code> | ||
| - e2e file: <code>exp/pretrain_Train_pytorch_train_specaug/results/model.val5.avg.best</code> | ||
| - e2e json file: <code>exp/pretrain_Train_pytorch_train_specaug/results/model.json</code> | ||
| - lm file: <code>exp/pretrainedlm/rnnlm.model.best</code> | ||
| - lm JSON file: <code>exp/pretrainedlm/model.json</code> | ||
| - dict file: <code>data/lang_char/pretrain_Train_unigram5000_units.txt</code> | ||
|
|
||
|
|
||
| ## Environments | ||
| - date: `Wed Feb 16 09:06:58 CET 2022` | ||
| - python version: `3.8.5 (default, Sep 4 2020, 07:30:14) [GCC 7.3.0]` | ||
| - espnet version: `espnet 0.9.8` | ||
| - chainer version: `chainer 6.0.0` | ||
| - pytorch version: `pytorch 1.4.0` | ||
| - Git hash: `19aabb415657c05a45467f9d8bb612db4764f6a1` | ||
| - Commit date: `Tue Oct 19 12:00:34 2021 +0200` | ||
|
|
||
|
|
||
| ### CER | ||
|
|
||
| |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| | ||
| |---|---|---|---|---|---|---|---|---| | ||
| |decode_Test_model.val5.avg.best_decode_|1243|12648|96.3|1.6|2.1|0.2|3.9|15.8| | ||
| |decode_Val_model.val5.avg.best_decode_|1082|14858|92.7|3.2|4.1|0.9|8.2|38.2| | ||
|
|
||
| ### WER | ||
|
|
||
| |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| | ||
| |---|---|---|---|---|---|---|---|---| | ||
| |decode_Test_model.val5.avg.best_decode_|1243|6660|96.2|2.1|1.7|0.4|4.2|15.7| | ||
| |decode_Val_model.val5.avg.best_decode_|1082|7866|91.6|4.7|3.7|1.0|9.4|38.2| |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,89 @@ | ||
| # ====== 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", "sge", "slurm", or "ssh" | ||
| cmd_backend='local' | ||
|
|
||
| # Local machine, without any Job scheduling system | ||
| if [ "${cmd_backend}" = local ]; then | ||
|
|
||
| # The other usage | ||
| export train_cmd="run.pl" | ||
| # Used for "*_train.py": "--gpu" is appended optionally by run.sh | ||
| export cuda_cmd="run.pl" | ||
| # Used for "*_recog.py" | ||
| export decode_cmd="run.pl" | ||
|
|
||
| # "qsub" (SGE, Torque, PBS, etc.) | ||
| elif [ "${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" | ||
|
|
||
| # "sbatch" (Slurm) | ||
| elif [ "${cmd_backend}" = slurm ]; then | ||
| # The default setting is written in conf/slurm.conf. | ||
| # You must change "-p cpu" and "-p gpu" for the "partion" for your environment. | ||
| # To know the "partion" names, type "sinfo". | ||
| # You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*" | ||
| # The devices are allocated exclusively using "${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/gpu.conf" | ||
| export decode_cmd="queue.pl --mem 4G" | ||
|
|
||
| else | ||
| echo "$0: Error: Unknown cmd_backend=${cmd_backend}" 1>&2 | ||
| return 1 | ||
| fi |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,7 @@ | ||
| batchsize: 0 | ||
| beam-size: 60 | ||
| ctc-weight: 0.4 | ||
| lm-weight: 0.6 | ||
| maxlenratio: 0.0 | ||
| minlenratio: 0.0 | ||
| penalty: 0.0 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,2 @@ | ||
| --sample-frequency=16000 | ||
| --num-mel-bins=80 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,10 @@ | ||
| # Default configuration | ||
| command qsub -v PATH -cwd -S /bin/bash -j y -l arch=*64* | ||
| 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 | ||
| default gpu=0 | ||
| option gpu=0 | ||
| option gpu=* -l 'hostname=b1[12345678]*|c*,gpu=$0' -q g.q |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| layer: 4 | ||
| unit: 2048 | ||
| opt: sgd # or adam | ||
| sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs | ||
| batchsize: 512 # batch size in LM training | ||
| epoch: 20 # if the data size is large, we can reduce this | ||
| patience: 3 | ||
| maxlen: 40 # if sentence length > lm_maxlen, lm_batchsize is automatically reduced | ||
| dropout-rate: 0.0 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1 @@ | ||
| --sample-frequency=16000 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,10 @@ | ||
| # Default configuration | ||
| command qsub -v PATH -cwd -S /bin/bash -j y -l arch=*64* | ||
| 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 | ||
| default gpu=0 | ||
| option gpu=0 | ||
| option gpu=* -l gpu=$0 -q g.q |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -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. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,16 @@ | ||
| process: | ||
| # these three processes are a.k.a. SpecAugument | ||
| - type: "time_warp" | ||
| max_time_warp: 5 | ||
| inplace: true | ||
| mode: "PIL" | ||
| - type: "freq_mask" | ||
| F: 30 | ||
| n_mask: 2 | ||
| inplace: true | ||
| replace_with_zero: false | ||
| - type: "time_mask" | ||
| T: 40 | ||
| n_mask: 2 | ||
| inplace: true | ||
| replace_with_zero: false |
Oops, something went wrong.