msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

refactor data pipe; fix conf; fix u2 default params

Browse Source
pull/578/head
Hui Zhang 4 years ago
parent c4df6bac32
commit 88d82b4ab8
10 changed files with 69 additions and 45 deletions
Show Stats Download Patch File Download Diff File

1
deepspeech/exps/u2/config.py
Unescape View File

@ -18,6 +18,7 @@ from deepspeech.exps.u2.model import U2Trainer
from deepspeech.io.dataset import ManifestDataset
from deepspeech.models.u2 import U2Model
_C = CfgNode()
_C.data = ManifestDataset.params()

2
deepspeech/frontend/normalizer.py
Unescape View File

@ -148,6 +148,8 @@ class FeatureNormalizer(object):
batch_size=64,
eps=1e-20):
"""Compute mean and std from randomly sampled instances."""
paddle.set_device('cpu')
collate_func = CollateFunc(featurize_func)
dataset = AudioDataset(manifest_path, num_samples, self._rng)
data_loader = DataLoader(

15
deepspeech/models/u2.py
Unescape View File

@ -61,12 +61,14 @@ class U2BaseModel(nn.Module):
def params(cls, config: Optional[CfgNode]=None) -> CfgNode:
# network architecture
default = CfgNode()
# allow add new item when merge_with_file
default.set_new_allowed(True)
default.cmvn_file = ""
default.cmvn_file_type = "npz"
default.input_dim = 0
default.output_dim = 0
# encoder related
default.encoder = 'conformer'
default.encoder = 'transformer'
default.encoder_conf = CfgNode(
dict(
output_size=256, # dimension of attention
@ -78,11 +80,12 @@ class U2BaseModel(nn.Module):
attention_dropout_rate=0.0,
input_layer='conv2d', # encoder input type, you can chose conv2d, conv2d6 and conv2d8
normalize_before=True,
cnn_module_kernel=15,
use_cnn_module=True,
activation_type='swish',
pos_enc_layer_type='rel_pos',
selfattention_layer_type='rel_selfattn', ))
# use_cnn_module=True,
# cnn_module_kernel=15,
# activation_type='swish',
# pos_enc_layer_type='rel_pos',
# selfattention_layer_type='rel_selfattn',
))
# decoder related
default.decoder = 'transformer'
default.decoder_conf = CfgNode(

8
examples/librispeech/s1/conf/chunk_confermer.yaml
Unescape View File

@ -1,11 +1,11 @@
# https://yaml.org/type/float.html
data:
train_manifest: data/manifest.tiny
dev_manifest: data/manifest.tiny
test_manifest: data/manifest.tiny
train_manifest: data/manifest.train
dev_manifest: data/manifest.dev
test_manifest: data/manifest.test
vocab_filepath: data/vocab.txt
unit_type: 'spm'
spm_model_prefix: 'data/bpe_unigram_200'
spm_model_prefix: 'data/bpe_unigram_5000'
mean_std_filepath: ""
augmentation_config: conf/augmentation.json
batch_size: 4

8
examples/librispeech/s1/conf/chunk_transformer.yaml
Unescape View File

@ -1,11 +1,11 @@
# https://yaml.org/type/float.html
data:
train_manifest: data/manifest.tiny
dev_manifest: data/manifest.tiny
test_manifest: data/manifest.tiny
train_manifest: data/manifest.train
dev_manifest: data/manifest.dev
test_manifest: data/manifest.test
vocab_filepath: data/vocab.txt
unit_type: 'spm'
spm_model_prefix: 'data/bpe_unigram_200'
spm_model_prefix: 'data/bpe_unigram_5000'
mean_std_filepath: ""
augmentation_config: conf/augmentation.json
batch_size: 64

6
examples/librispeech/s1/conf/conformer.yaml
Unescape View File

@ -1,8 +1,8 @@
# https://yaml.org/type/float.html
data:
train_manifest: data/manifest.tiny
dev_manifest: data/manifest.tiny
test_manifest: data/manifest.tiny
train_manifest: data/manifest.train
dev_manifest: data/manifest.dev
test_manifest: data/manifest.test
vocab_filepath: data/vocab.txt
unit_type: 'spm'
spm_model_prefix: 'data/bpe_unigram_5000'

8
examples/librispeech/s1/conf/transformer.yaml
Unescape View File

@ -1,11 +1,11 @@
# https://yaml.org/type/float.html
data:
train_manifest: data/manifest.tiny
dev_manifest: data/manifest.tiny
test_manifest: data/manifest.tiny
train_manifest: data/manifest.train
dev_manifest: data/manifest.dev
test_manifest: data/manifest.test
vocab_filepath: data/vocab.txt
unit_type: 'spm'
spm_model_prefix: 'data/bpe_unigram_200'
spm_model_prefix: 'data/bpe_unigram_5000'
mean_std_filepath: ""
augmentation_config: conf/augmentation.json
batch_size: 64

24
examples/librispeech/s1/local/data.sh
Unescape View File

@ -27,8 +27,20 @@ if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
exit 1
fi
for set in train-clean-100 train-clean-360 train-other-500 dev-clean dev-other test-clean test-other; do
mv data/manifest.${set} data/manifest.${set}.raw
done
for set in train-clean-100 train-clean-360 train-other-500; do
cat data/manifest.${set} >> data/manifest.train.raw
cat data/manifest.${set}.raw >> data/manifest.train.raw
done
for set in dev-clean dev-other; do
cat data/manifest.${set}.raw >> data/manifest.dev.raw
done
for set in test-clean test-other; do
cat data/manifest.${set}.raw >> data/manifest.test.raw
done
fi
@ -73,20 +85,24 @@ fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
# format manifest with tokenids, vocab size
for set in train dev test dev-clean dev-other test-clean test-other; do
{
python3 ${MAIN_ROOT}/utils/format_data.py \
--feat_type "raw" \
--cmvn_path "data/mean_std.json" \
--unit_type "spm" \
--spm_model_prefix ${bpeprefix} \
--vocab_path="data/vocab.txt" \
--manifest_path="data/manifest.train.raw" \
--output_path="data/manifest.train"
--manifest_path="data/manifest.${set}.raw" \
--output_path="data/manifest.${set}"
if [ $? -ne 0 ]; then
echo "Formt mnaifest failed. Terminated."
exit 1
fi
}&
done
wait
fi
echo "LibriSpeech Data preparation done."

9
examples/librispeech/s1/run.sh
Unescape View File

@ -4,7 +4,8 @@ source path.sh
stage=0
stop_stage=100
ckpt=conformer
conf_path=conf/transformer.yaml
ckpt=$(basename ${conf_path} | awk -F'.' '{print $1}')
avg_num=30
avg_ckpt=avg_${avg_num}
@ -17,7 +18,7 @@ fi
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
# train model, all `ckpt` under `exp` dir
CUDA_VISIBLE_DEVICES=4,5,6,7 ./local/train.sh conf/conformer.yaml ${ckpt}
CUDA_VISIBLE_DEVICES=4,5,6,7 ./local/train.sh ${conf_path} ${ckpt}
fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
@ -27,10 +28,10 @@ fi
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
# test ckpt avg_n
CUDA_VISIBLE_DEVICES=7 ./local/test.sh conf/conformer.yaml exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1
CUDA_VISIBLE_DEVICES=7 ./local/test.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1
fi
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
# export ckpt avg_n
CUDA_VISIBLE_DEVICES= ./local/export.sh conf/conformer.yaml exp/${ckpt}/checkpoints/${avg_ckpt} exp/${ckpt}/checkpoints/${avg_ckpt}.jit
CUDA_VISIBLE_DEVICES= ./local/export.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} exp/${ckpt}/checkpoints/${avg_ckpt}.jit
fi

9
examples/tiny/s1/run.sh
Unescape View File

@ -4,7 +4,8 @@ source path.sh
stage=0
stop_stage=100
ckpt=conformer
conf_path=conf/transformer.yaml
ckpt=$(basename ${conf_path} | awk -F'.' '{print $1}')
avg_num=1
avg_ckpt=avg_${avg_num}
@ -17,7 +18,7 @@ fi
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
# train model, all `ckpt` under `exp` dir
CUDA_VISIBLE_DEVICES=0 ./local/train.sh conf/conformer.yaml ${ckpt}
CUDA_VISIBLE_DEVICES=4,5,6,7 ./local/train.sh ${conf_path} ${ckpt}
fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
@ -27,10 +28,10 @@ fi
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
# test ckpt avg_n
CUDA_VISIBLE_DEVICES=0 ./local/test.sh conf/conformer.yaml exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1
CUDA_VISIBLE_DEVICES=7 ./local/test.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} || exit -1
fi
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
# export ckpt avg_n
CUDA_VISIBLE_DEVICES= ./local/export.sh conf/conformer.yaml exp/${ckpt}/checkpoints/${avg_ckpt} exp/${ckpt}/checkpoints/${avg_ckpt}.jit
CUDA_VISIBLE_DEVICES= ./local/export.sh ${conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} exp/${ckpt}/checkpoints/${avg_ckpt}.jit
fi

Write Preview
Loading…
Cancel
Save