# MIT License
#
# Copyright (c) 2021 Soohwan Kim
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
from omegaconf import DictConfig
from openspeech.models import register_model
from openspeech.models import OpenspeechCTCModel
from openspeech.encoders.quartznet import QuartzNet
from openspeech.tokenizers.tokenizer import Tokenizer
from openspeech.models.quartznet.configurations import (
QuartzNet5x5Configs,
QuartzNet10x5Configs,
QuartzNet15x5Configs,
)
[docs]@register_model('quartznet5x5', dataclass=QuartzNet5x5Configs)
class QuartzNet5x5Model(OpenspeechCTCModel):
r"""
QUARTZNET: DEEP AUTOMATIC SPEECH RECOGNITION WITH 1D TIME-CHANNEL SEPARABLE CONVOLUTIONS
Paper: https://arxiv.org/abs/1910.10261.pdf
Args:
configs (DictConfig): configuration set.
tokenizer (Tokeizer): tokenizer is in charge of preparing the inputs for a model.
Inputs:
inputs (torch.FloatTensor): A input sequence passed to encoders. Typically for inputs this will be a padded `FloatTensor` of size ``(batch, seq_length, dimension)``.
input_lengths (torch.LongTensor): The length of input tensor. ``(batch)``
Returns:
outputs (dict): Result of model predictions that contains `y_hats`, `logits`, `output_lengths`
"""
def __init__(self, configs: DictConfig, tokenizer: Tokenizer) -> None:
super(QuartzNet5x5Model, self).__init__(configs, tokenizer)
def build_model(self):
self.encoder = QuartzNet(
configs=self.configs,
input_dim=self.configs.audio.num_mels,
num_classes=self.num_classes,
)
[docs]@register_model('quartznet10x5', dataclass=QuartzNet10x5Configs)
class QuartzNet10x5Model(QuartzNet5x5Model):
r"""
QUARTZNET: DEEP AUTOMATIC SPEECH RECOGNITION WITH 1D TIME-CHANNEL SEPARABLE CONVOLUTIONS
Paper: https://arxiv.org/abs/1910.10261.pdf
Args:
configs (DictConfig): configuration set.
tokenizer (Tokeizer): tokenizer is in charge of preparing the inputs for a model.
Inputs:
inputs (torch.FloatTensor): A input sequence passed to encoders. Typically for inputs this will be a padded `FloatTensor` of size ``(batch, seq_length, dimension)``.
input_lengths (torch.LongTensor): The length of input tensor. ``(batch)``
Returns:
outputs (dict): Result of model predictions that contains `y_hats`, `logits`, `output_lengths`
"""
def __init__(self, configs: DictConfig, tokenizer: Tokenizer) -> None:
super(QuartzNet10x5Model, self).__init__(configs, tokenizer)
[docs]@register_model('quartznet15x5', dataclass=QuartzNet15x5Configs)
class QuartzNet15x5Model(QuartzNet5x5Model):
r"""
QUARTZNET: DEEP AUTOMATIC SPEECH RECOGNITION WITH 1D TIME-CHANNEL SEPARABLE CONVOLUTIONS
Paper: https://arxiv.org/abs/1910.10261.pdf
Args:
configs (DictConfig): configuration set.
tokenizer (Tokeizer): tokenizer is in charge of preparing the inputs for a model.
Inputs:
inputs (torch.FloatTensor): A input sequence passed to encoders. Typically for inputs this will be a padded `FloatTensor` of size ``(batch, seq_length, dimension)``.
input_lengths (torch.LongTensor): The length of input tensor. ``(batch)``
Returns:
outputs (dict): Result of model predictions that contains `y_hats`, `logits`, `output_lengths`
"""
def __init__(self, configs: DictConfig, tokenizer: Tokenizer) -> None:
super(QuartzNet15x5Model, self).__init__(configs, tokenizer)