Merge pull request espnet#5605 from linyueqian/master

[WIP] KiSingV2 Recipe
Emrys365 · Dec 30, 2023 · f732a75 · f732a75
2 parents 7c140c2 + 51a6ccf
commit f732a75
Show file tree

Hide file tree

Showing 25 changed files with 2,035 additions and 0 deletions.
diff --git a/egs2/README.md b/egs2/README.md
@@ -85,6 +85,7 @@ See: https://espnet.github.io/espnet/espnet2_tutorial.html#recipes-using-espnet2
 | jv_openslr35            | Javanese                                                                                                                         | ASR                     | JAV                  | http://www.openslr.org/35                                                                                    |              |
 | jvs                     | JVS (Japanese versatile speech) corpus                                                                                           | TTS                     | JPN                  | https://sites.google.com/site/shinnosuketakamichi/research-topics/jvs_corpus                                 |              |
 | kathbath                     |    Kathbath dataset                                           | ASR                     | 12 Indian langauges                  | https://ai4bharat.iitm.ac.in/indic-superb                                 |              |
+| kising | KiSing-v2 Corpus (ACESinger augmented)                                                                                                 | SVS                     | CMN                   | WIP                                                                                  |              |
 | ksponspeech             | KsponSpeech (Korean spontaneous speech) corpus                                                                                   | ASR                     | KOR                  | https://aihub.or.kr/aidata/105                                                                               |              |
 | ksc                     | Kazakh speech corpus                                     |              |                                                        | ASR                     | KAZ                  | https://www.openslr.org/102/                                                                                 |              |
 | kss                     | Korean single speaker corpus                                                                                                     | TTS                     | KOR                  | https://www.kaggle.com/bryanpark/korean-single-speaker-speech-dataset                                        |              |

diff --git a/egs2/TEMPLATE/asr1/db.sh b/egs2/TEMPLATE/asr1/db.sh
@@ -91,6 +91,7 @@ JSSS=downloads
 JSUT=downloads
 JTUBESPEECH=downloads
 JVS=downloads
+KISING=downloads
 KSC=downloads
 KSS=
 QASR_TTS=downloads

diff --git a/egs2/kising/svs1/README.md b/egs2/kising/svs1/README.md
@@ -0,0 +1,31 @@
+# ACESinger-KiSing-V2 RECIPE
+
+This is the recipe of ACESinger-augmented KiSing-V2 recipe
+
+You should download the original and augmented KiSing dataset and make sure the file structure is like this:
+
+```
+KISING
+├── 421
+│   ├── ...
+├── 422
+│   ├── ...
+│   ...
+├── 443
+│   ├── ...
+├── original
+│   ├── 421_all.wav
+│   ├── ...
+```
+
+
+
+See the following pages for the usage:
+- [How to run the recipe](../../TEMPLATE/svs1/README.md#how-to-run)
+- [How to train NaiveRNN](../../TEMPLATE/tts1/README.md#naive_rnn-training)
+- [How to train XiaoiceSing](../../TEMPLATE/tts1/README.md#xiaoicesing-training)
+- [How to train VISinger1+2](../../TEMPLATE/tts1/README.md#visinger-12-training)
+
+See the following pages before asking the question:
+- [ESPnet2 Tutorial](https://espnet.github.io/espnet/espnet2_tutorial.html)
+- [ESPnet2 SVS FAQ](../../TEMPLATE/svs1/README.md#faq)
diff --git a/egs2/kising/svs1/cmd.sh b/egs2/kising/svs1/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
diff --git a/egs2/kising/svs1/conf/pbs.conf b/egs2/kising/svs1/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
diff --git a/egs2/kising/svs1/conf/queue.conf b/egs2/kising/svs1/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
diff --git a/egs2/kising/svs1/conf/slurm.conf b/egs2/kising/svs1/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.
diff --git a/egs2/kising/svs1/conf/tuning/decode_vits.yaml b/egs2/kising/svs1/conf/tuning/decode_vits.yaml
@@ -0,0 +1,8 @@
+# This configuration is the decoding setting for VITS.
+
+##########################################################
+#                    DECODING SETTING                    #
+##########################################################
+noise_scale: 0.667         # noise scale parameter for the flow in VITS.
+noise_scale_dur: 0.8       # noise scale parameter for the stochastic duration predictor in VITS.
+use_teacher_forcing: false # whether to use teacher forcing.