mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +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.
44 lines
1.6 KiB
Python
44 lines
1.6 KiB
Python
# 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.
|
|
|
|
from typing import Tuple
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
|
|
|
|
class EncoderInterface(nn.Module):
|
|
def forward(
|
|
self, x: torch.Tensor, x_lens: torch.Tensor
|
|
) -> Tuple[torch.Tensor, torch.Tensor]:
|
|
"""
|
|
Args:
|
|
x:
|
|
A tensor of shape (batch_size, input_seq_len, num_features)
|
|
containing the input features.
|
|
x_lens:
|
|
A tensor of shape (batch_size,) containing the number of frames
|
|
in `x` before padding.
|
|
Returns:
|
|
Return a tuple containing two tensors:
|
|
- encoder_out, a tensor of (batch_size, out_seq_len, output_dim)
|
|
containing unnormalized probabilities, i.e., the output of a
|
|
linear layer.
|
|
- encoder_out_lens, a tensor of shape (batch_size,) containing
|
|
the number of frames in `encoder_out` before padding.
|
|
"""
|
|
raise NotImplementedError("Please implement it in a subclass")
|