mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 01:52:41 +00:00
1d44da845b
* Begin to add RNN-T training for librispeech. * Copy files from conformer_ctc. Will edit it. * Use conformer/transformer model as encoder. * Begin to add training script. * Add training code. * Remove long utterances to avoid OOM when a large max_duraiton is used. * Begin to add decoding script. * Add decoding script. * Minor fixes. * Add beam search. * Use LSTM layers for the encoder. Need more tunings. * Use stateless decoder. * Minor fixes to make it ready for merge. * Fix README. * Update RESULT.md to include RNN-T Conformer. * Minor fixes. * Fix tests. * Minor fixes. * Minor fixes. * Fix tests.
61 lines
1.5 KiB
Python
Executable File
61 lines
1.5 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
# Copyright 2021 Xiaomi Corp. (authors: Fangjun Kuang)
|
|
#
|
|
# See ../../../../LICENSE for clarification regarding multiple authors
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
"""
|
|
To run this file, do:
|
|
|
|
cd icefall/egs/librispeech/ASR
|
|
python ./transducer/test_conformer.py
|
|
"""
|
|
|
|
import torch
|
|
from conformer import Conformer
|
|
|
|
|
|
def test_conformer():
|
|
output_dim = 1024
|
|
conformer = Conformer(
|
|
num_features=80,
|
|
output_dim=output_dim,
|
|
subsampling_factor=4,
|
|
d_model=512,
|
|
nhead=8,
|
|
dim_feedforward=2048,
|
|
num_encoder_layers=12,
|
|
use_feat_batchnorm=True,
|
|
)
|
|
N = 3
|
|
T = 100
|
|
C = 80
|
|
x = torch.randn(N, T, C)
|
|
x_lens = torch.tensor([50, 100, 80])
|
|
logits, logit_lens = conformer(x, x_lens)
|
|
|
|
expected_T = ((T - 1) // 2 - 1) // 2
|
|
assert logits.shape == (N, expected_T, output_dim)
|
|
assert logit_lens.max().item() == expected_T
|
|
print(logits.shape)
|
|
print(logit_lens)
|
|
|
|
|
|
def main():
|
|
test_conformer()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|