Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Do some changes for aishell/ASR/transducer stateless/export.py #347

Merged
merged 3 commits into from
May 7, 2022
Merged

Do some changes for aishell/ASR/transducer stateless/export.py #347

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7c6a9bd
do some changes for aishell/ASR/transducer_stateless/export.py
luomingshuang May 6, 2022
ac6d660
do some changes for export.py
luomingshuang May 6, 2022
39f43bc
do some changes for export.py
luomingshuang May 6, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 11 additions & 12 deletions egs/aishell/ASR/transducer_stateless/export.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
#!/usr/bin/env python3
#
# Copyright 2021 Xiaomi Corporation (Author: Fangjun Kuang)
# 2022 Xiaomi Corporation (Author: Mingshuang Luo)
#
# See ../../../../LICENSE for clarification regarding multiple authors
#
Expand All @@ -22,7 +23,7 @@
Usage:
./transducer_stateless/export.py \
--exp-dir ./transducer_stateless/exp \
--bpe-model data/lang_bpe_500/bpe.model \
--lang-dir data/lang_char \
--epoch 20 \
--avg 10

Expand All @@ -33,20 +34,19 @@
cd /path/to/exp_dir
ln -s pretrained.pt epoch-9999.pt

cd /path/to/egs/librispeech/ASR
cd /path/to/egs/aishell/ASR
./transducer_stateless/decode.py \
--exp-dir ./transducer_stateless/exp \
--epoch 9999 \
--avg 1 \
--max-duration 1 \
--bpe-model data/lang_bpe_500/bpe.model
--lang-dir data/lang_char
"""

import argparse
import logging
from pathlib import Path

import sentencepiece as spm
import torch
import torch.nn as nn
from conformer import Conformer
Expand All @@ -56,6 +56,7 @@

from icefall.checkpoint import average_checkpoints, load_checkpoint
from icefall.env import get_env_info
from icefall.lexicon import Lexicon
from icefall.utils import AttributeDict, str2bool


Expand Down Expand Up @@ -91,10 +92,10 @@ def get_parser():
)

parser.add_argument(
"--bpe-model",
"--lang-dir",
type=str,
default="data/lang_bpe_500/bpe.model",
help="Path to the BPE model",
default="data/lang_char",
help="The lang dir",
)

parser.add_argument(
Expand Down Expand Up @@ -194,12 +195,10 @@ def main():

logging.info(f"device: {device}")

sp = spm.SentencePieceProcessor()
sp.load(params.bpe_model)
lexicon = Lexicon(params.lang_dir)

# <blk> is defined in local/train_bpe_model.py
params.blank_id = sp.piece_to_id("<blk>")
params.vocab_size = sp.get_piece_size()
params.blank_id = 0
params.vocab_size = max(lexicon.tokens) + 1

logging.info(params)

Expand Down