-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #4642 from massabaali7/master
qasr update
- Loading branch information
Showing
28 changed files
with
790 additions
and
0 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,19 @@ | ||
# QASR-TTS RECIPE | ||
|
||
- Our goal is to build a TTS character based system using semi-supervised data selection in a low-resource scenario by proposing two different methodologies: | ||
the first one by training non-autoregressive (non-AR) model from scratch on very small amount of data; and the second one by training | ||
autoregressive (AR) model finetuned on top of a pre-trained model. | ||
|
||
- Step 1: Prepare the data | ||
|
||
- Step 2: Download a pretrained model | ||
|
||
- Step 3: Replace token list with the pretrained model's one | ||
|
||
- Step 4: Finetune the pre-trained model on our 1 hour dataset and we excluded the embedding layer since we are finetuning on a different language | ||
|
||
- Step 5: Use the finetuned model as a teacher model to train the Non-AR model FastSpeech2 | ||
|
||
- Step 6: Train Parallel Wav GAN model to produce better wav samples | ||
|
||
Go to this link to download the dataset: https://arabicspeech.org/qasr_tts |
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 +1,32 @@ | ||
- Environments | ||
|
||
- python version: `3.8.12` | ||
|
||
- espnet version: `espnet 0.10.7a1` | ||
|
||
- chainer version: `chainer 6.0.0` | ||
|
||
- pytorch version: `pytorch 1.10.0` | ||
|
||
|
||
|
||
- Model files | ||
|
||
- training config file (teacher model): `./conf/tuning/finetune_transformer.yaml` | ||
|
||
- training config file: `./conf/tuning/train_conformer_fastspeech2.yaml` | ||
|
||
|
||
|
||
- Results: {using our pretrained ASR model on MGB2 data} here is the recipe "egs/mgb2" | ||
|
||
- FastSpeech2 (Trans.) w/ PWG: (R = 1) | ||
|
||
- CER: 3.9 | ||
|
||
- WER: 9.13 | ||
|
||
- MOS | ||
|
||
- intelligibility: 4.4 ± 0.06 | ||
- naturalness: 4.2 ± 0.06 |
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 +1,32 @@ | ||
# Copyright 2021 Massa Baali | ||
|
||
pretrained_model=$1 | ||
# From data preparation to statistics calculation | ||
./run.sh --stage 1 --stop_stage 5 | ||
|
||
# download pretrained model kan-bayashi/ljspeech_tts_train_transformer_raw_char_tacotron_train.loss.ave | ||
wget ${pretrained} | ||
|
||
# Replace token list with pretrained model's one | ||
pyscripts/utils/make_token_list_from_config.py pretrained_model_path/exp/ljspeech_tts_train_transformer_raw_char_tacotron/config.yaml | ||
# tokens.txt is created in model directory | ||
mv dump/token_list/ljspeech_tts_train_transformer_raw_char_tacotron/tokens.{txt,txt.bak} | ||
ln -s pretrained_dir/exp/ljspeech_tts_train_transformer_raw_char_tacotron/tokens.txt dump/token_list/new_model | ||
|
||
# Train the model | ||
./run.sh --stage 6 --train_config conf/tuning/finetune_transformer.yaml --train_args \ | ||
"--init_param pretrained_model/exp/tts_train_transformer_raw_char_tacotron/train.loss.ave_5best.pth":::tts.enc.embed \ | ||
--tag finetune_pretrained_transformers | ||
|
||
# Now the trained model above will be used as a teacher model for the Non-AR model FastSpeech2 | ||
# Prepare durations file | ||
./run.sh --stage 7 --tts_exp exp/tts_finetune_pretrained_transformers \ | ||
--inference_args "--use_teacher_forcing true" \ | ||
--test_sets "tr_no_dev dev eval1" | ||
|
||
# Since fastspeech2 requires extra feature calculation, run from stage 5. | ||
./run.sh --stage 5 \ | ||
--train_config conf/tuning/train_conformer_fastspeech2.yaml \ | ||
--teacher_dumpdir exp/tts_finetune_pretrained_transformers/decode_use_teacher_forcingtrue_train.loss.ave \ | ||
--tts_stats_dir exp/tts_finetune_pretrained_transformers/decode_use_teacher_forcingtrue_train.loss.ave/stats \ | ||
--write_collected_feats true |
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 +1,110 @@ | ||
# ====== 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 |
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 @@ | ||
tuning/decode_tacotron2.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 +1,11 @@ | ||
# 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 |
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 +1,12 @@ | ||
# 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 |
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 @@ | ||
tuning/finetune_transformer.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 +1,10 @@ | ||
# This configuration is the decoding setting for FastSpeech or FastSpeech2. | ||
|
||
########################################################## | ||
# DECODING SETTING # | ||
########################################################## | ||
speed_control_alpha: 1 # alpha to control the speed of generated speech | ||
# 1 < alpha makes slower and 1 > alpha makes faster | ||
use_teacher_forcing: false # whether to use teacher forcing | ||
# if true, we use groundtruth of durations | ||
# (+ pitch & energy for FastSpeech2) |
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 @@ | ||
# This configuration is the basic decoding setting for Tacotron 2. | ||
# It can be also applied to Transformer. If you met some problems | ||
# such as deletions or repetitions, it is worthwhile to try | ||
# `use_att_constraint: true` to make the generation more stable. | ||
# Note that attention constraint is not supported in Transformer. | ||
|
||
########################################################## | ||
# DECODING SETTING # | ||
########################################################## | ||
threshold: 0.5 # threshold to stop the generation | ||
maxlenratio: 10.0 # maximum length of generated samples = input length * maxlenratio | ||
minlenratio: 0.0 # minimum length of generated samples = input length * minlenratio | ||
use_att_constraint: true # whether to use attention constraint, which is introduced in deep voice 3 | ||
backward_window: 1 # backward window size in the attention constraint | ||
forward_window: 3 # forward window size in the attention constraint | ||
use_teacher_forcing: false # whether to use teacher forcing |
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 +1,78 @@ | ||
# This configuration is for ESPnet2 to finetune Tacotron 2. Compared to the | ||
# original paper, this configuration additionally use the guided attention | ||
# loss to accelerate the learning of the diagonal attention. It requires | ||
# only a single GPU with 12 GB memory and it takes ~1 days to finish the | ||
# training on Titan V. | ||
|
||
########################################################## | ||
# TTS MODEL SETTING # | ||
########################################################## | ||
tts: tacotron2 # model architecture | ||
tts_conf: # keyword arguments for the selected model | ||
embed_dim: 512 # char or phn embedding dimension | ||
elayers: 1 # number of blstm layers in encoder | ||
eunits: 512 # number of blstm units | ||
econv_layers: 3 # number of convolutional layers in encoder | ||
econv_chans: 512 # number of channels in convolutional layer | ||
econv_filts: 5 # filter size of convolutional layer | ||
atype: location # attention function type | ||
adim: 512 # attention dimension | ||
aconv_chans: 32 # number of channels in convolutional layer of attention | ||
aconv_filts: 15 # filter size of convolutional layer of attention | ||
cumulate_att_w: true # whether to cumulate attention weight | ||
dlayers: 2 # number of lstm layers in decoder | ||
dunits: 1024 # number of lstm units in decoder | ||
prenet_layers: 2 # number of layers in prenet | ||
prenet_units: 256 # number of units in prenet | ||
postnet_layers: 5 # number of layers in postnet | ||
postnet_chans: 512 # number of channels in postnet | ||
postnet_filts: 5 # filter size of postnet layer | ||
output_activation: null # activation function for the final output | ||
use_batch_norm: true # whether to use batch normalization in encoder | ||
use_concate: true # whether to concatenate encoder embedding with decoder outputs | ||
use_residual: false # whether to use residual connection in encoder | ||
dropout_rate: 0.5 # dropout rate | ||
zoneout_rate: 0.1 # zoneout rate | ||
reduction_factor: 1 # reduction factor | ||
spk_embed_dim: null # speaker embedding dimension | ||
use_masking: true # whether to apply masking for padded part in loss calculation | ||
bce_pos_weight: 5.0 # weight of positive sample in binary cross entropy calculation | ||
use_guided_attn_loss: true # whether to use guided attention loss | ||
guided_attn_loss_sigma: 0.4 # sigma of guided attention loss | ||
guided_attn_loss_lambda: 1.0 # strength of guided attention loss | ||
|
||
########################################################## | ||
# OPTIMIZER SETTING # | ||
########################################################## | ||
optim: adam # optimizer type | ||
optim_conf: # keyword arguments for selected optimizer | ||
lr: 1.0e-04 # learning rate | ||
eps: 1.0e-06 # epsilon | ||
weight_decay: 0.0 # weight decay coefficient | ||
|
||
########################################################## | ||
# OTHER TRAINING SETTING # | ||
########################################################## | ||
num_iters_per_epoch: 200 # number of iters per epoch | ||
max_epoch: 100 # number of epochs | ||
grad_clip: 1.0 # gradient clipping norm | ||
grad_noise: false # whether to use gradient noise injection | ||
accum_grad: 1 # gradient accumulation | ||
# batch_bins: 1000000 # batch bins (for feats_type=fbank) | ||
batch_bins: 3750000 # batch bins (for feats_type=raw, *= n_shift / n_mels) | ||
batch_type: numel # how to make batch | ||
sort_in_batch: descending # how to sort data in making batch | ||
sort_batch: descending # how to sort created batches | ||
num_workers: 1 # number of workers of data loader | ||
train_dtype: float32 # dtype in training | ||
log_interval: null # log interval in iterations | ||
keep_nbest_models: 5 # number of models to keep | ||
num_att_plot: 3 # number of attention figures to be saved in every check | ||
seed: 0 # random seed number | ||
best_model_criterion: | ||
- - valid | ||
- loss | ||
- min | ||
- - train | ||
- loss | ||
- min |
Oops, something went wrong.