mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 10:02:22 +00:00
6e609c67a2
* support streaming in conformer * Add more documents * support streaming on pruned_transducer_stateless2; add delay penalty; fixes for decode states * Minor fixes * streaming for pruned_transducer_stateless4 * Fix conv cache error, support async streaming decoding * Fix style * Fix style * Fix style * Add torch.jit.export * mask the initial cache * Cutting off invalid frames of encoder_embed output * fix relative positional encoding in streaming decoding for compution saving * Minor fixes * Minor fixes * Minor fixes * Minor fixes * Minor fixes * Fix jit export for torch 1.6 * Minor fixes for streaming decoding * Minor fixes on decode stream * move model parameters to train.py * make states in forward streaming optional * update pretrain to support streaming model * update results.md * update tensorboard and pre-models * fix typo * Fix tests * remove unused arguments * add streaming decoding ci * Minor fix * Minor fix * disable right context by default
70 lines
2.2 KiB
Python
70 lines
2.2 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.
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
from scaling import ScaledLinear
|
|
|
|
|
|
class Joiner(nn.Module):
|
|
def __init__(
|
|
self,
|
|
encoder_dim: int,
|
|
decoder_dim: int,
|
|
joiner_dim: int,
|
|
vocab_size: int,
|
|
):
|
|
super().__init__()
|
|
|
|
self.encoder_proj = ScaledLinear(encoder_dim, joiner_dim)
|
|
self.decoder_proj = ScaledLinear(decoder_dim, joiner_dim)
|
|
self.output_linear = ScaledLinear(joiner_dim, vocab_size)
|
|
|
|
def forward(
|
|
self,
|
|
encoder_out: torch.Tensor,
|
|
decoder_out: torch.Tensor,
|
|
project_input: bool = True,
|
|
) -> torch.Tensor:
|
|
"""
|
|
Args:
|
|
encoder_out:
|
|
Output from the encoder. Its shape is (N, T, s_range, C).
|
|
decoder_out:
|
|
Output from the decoder. Its shape is (N, T, s_range, C).
|
|
project_input:
|
|
If true, apply input projections encoder_proj and decoder_proj.
|
|
If this is false, it is the user's responsibility to do this
|
|
manually.
|
|
Returns:
|
|
Return a tensor of shape (N, T, s_range, C).
|
|
"""
|
|
|
|
assert encoder_out.ndim == decoder_out.ndim
|
|
assert encoder_out.ndim in (2, 4)
|
|
assert encoder_out.shape == decoder_out.shape
|
|
|
|
if project_input:
|
|
logit = self.encoder_proj(encoder_out) + self.decoder_proj(
|
|
decoder_out
|
|
)
|
|
else:
|
|
logit = encoder_out + decoder_out
|
|
|
|
logit = self.output_linear(torch.tanh(logit))
|
|
|
|
return logit
|