From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/tasks/vad.py | 104 ++++++++++++++++++++-------------------------------
1 files changed, 41 insertions(+), 63 deletions(-)
diff --git a/funasr/tasks/vad.py b/funasr/tasks/vad.py
index 22a5cb3..822be22 100644
--- a/funasr/tasks/vad.py
+++ b/funasr/tasks/vad.py
@@ -1,77 +1,40 @@
import argparse
import logging
+import os
+from pathlib import Path
from typing import Callable
from typing import Collection
from typing import Dict
from typing import List
from typing import Optional
from typing import Tuple
-import os
-from pathlib import Path
-from typing import Tuple
from typing import Union
-import yaml
+
import numpy as np
import torch
-from typeguard import check_argument_types
-from typeguard import check_return_type
+import yaml
from funasr.datasets.collate_fn import CommonCollateFn
-from funasr.datasets.preprocessor import CommonPreprocessor
-from funasr.models.ctc import CTC
-from funasr.models.decoder.abs_decoder import AbsDecoder
-from funasr.models.decoder.rnn_decoder import RNNDecoder
-from funasr.models.decoder.transformer_decoder import (
- DynamicConvolution2DTransformerDecoder, # noqa: H301
-)
-from funasr.models.decoder.transformer_decoder import DynamicConvolutionTransformerDecoder
-from funasr.models.decoder.transformer_decoder import (
- LightweightConvolution2DTransformerDecoder, # noqa: H301
-)
-from funasr.models.decoder.transformer_decoder import (
- LightweightConvolutionTransformerDecoder, # noqa: H301
-)
-from funasr.models.decoder.transformer_decoder import TransformerDecoder
-from funasr.models.encoder.abs_encoder import AbsEncoder
-from funasr.models.encoder.conformer_encoder import ConformerEncoder
-from funasr.models.encoder.data2vec_encoder import Data2VecEncoder
-from funasr.models.encoder.rnn_encoder import RNNEncoder
-from funasr.models.encoder.transformer_encoder import TransformerEncoder
-from funasr.models.frontend.abs_frontend import AbsFrontend
-from funasr.models.frontend.default import DefaultFrontend
-from funasr.models.frontend.fused import FusedFrontends
-from funasr.models.frontend.wav_frontend import WavFrontend
-from funasr.models.frontend.s3prl import S3prlFrontend
-from funasr.models.frontend.windowing import SlidingWindow
-from funasr.models.postencoder.abs_postencoder import AbsPostEncoder
-from funasr.models.postencoder.hugging_face_transformers_postencoder import (
- HuggingFaceTransformersPostEncoder, # noqa: H301
-)
-from funasr.models.preencoder.abs_preencoder import AbsPreEncoder
-from funasr.models.preencoder.linear import LinearProjection
-from funasr.models.preencoder.sinc import LightweightSincConvs
-from funasr.models.specaug.abs_specaug import AbsSpecAug
-from funasr.models.specaug.specaug import SpecAug
from funasr.layers.abs_normalize import AbsNormalize
from funasr.layers.global_mvn import GlobalMVN
from funasr.layers.utterance_mvn import UtteranceMVN
-from funasr.tasks.abs_task import AbsTask
-from funasr.text.phoneme_tokenizer import g2p_choices
-from funasr.train.abs_espnet_model import AbsESPnetModel
-from funasr.train.class_choices import ClassChoices
-from funasr.train.trainer import Trainer
-from funasr.utils.get_default_kwargs import get_default_kwargs
-from funasr.utils.nested_dict_action import NestedDictAction
-from funasr.utils.types import float_or_none
-from funasr.utils.types import int_or_none
-from funasr.utils.types import str2bool
-from funasr.utils.types import str_or_none
-
-from funasr.models.specaug.specaug import SpecAugLFR
-from funasr.models.predictor.cif import CifPredictor, CifPredictorV2
-from funasr.modules.subsampling import Conv1dSubsampling
from funasr.models.e2e_vad import E2EVadModel
from funasr.models.encoder.fsmn_encoder import FSMN
+from funasr.models.frontend.abs_frontend import AbsFrontend
+from funasr.models.frontend.default import DefaultFrontend
+from funasr.models.frontend.fused import FusedFrontends
+from funasr.models.frontend.s3prl import S3prlFrontend
+from funasr.models.frontend.wav_frontend import WavFrontend, WavFrontendOnline
+from funasr.models.frontend.windowing import SlidingWindow
+from funasr.models.specaug.abs_specaug import AbsSpecAug
+from funasr.models.specaug.specaug import SpecAug
+from funasr.models.specaug.specaug import SpecAugLFR
+from funasr.tasks.abs_task import AbsTask
+from funasr.train.class_choices import ClassChoices
+from funasr.train.trainer import Trainer
+from funasr.utils.types import float_or_none
+from funasr.utils.types import int_or_none
+from funasr.utils.types import str_or_none
frontend_choices = ClassChoices(
name="frontend",
@@ -81,6 +44,7 @@
s3prl=S3prlFrontend,
fused=FusedFrontends,
wav_frontend=WavFrontend,
+ wav_frontend_online=WavFrontendOnline,
),
type_check=AbsFrontend,
default="default",
@@ -226,7 +190,6 @@
[Collection[Tuple[str, Dict[str, np.ndarray]]]],
Tuple[List[str], Dict[str, torch.Tensor]],
]:
- assert check_argument_types()
# NOTE(kamo): int value = 0 is reserved by CTC-blank symbol
return CommonCollateFn(float_pad_value=0.0, int_pad_value=-1)
@@ -234,7 +197,6 @@
def build_preprocess_fn(
cls, args: argparse.Namespace, train: bool
) -> Optional[Callable[[str, Dict[str, np.array]], Dict[str, np.ndarray]]]:
- assert check_argument_types()
# if args.use_preprocessor:
# retval = CommonPreprocessor(
# train=train,
@@ -257,7 +219,6 @@
# else:
# retval = None
retval = None
- assert check_return_type(retval)
return retval
@classmethod
@@ -276,12 +237,10 @@
cls, train: bool = True, inference: bool = False
) -> Tuple[str, ...]:
retval = ()
- assert check_return_type(retval)
return retval
@classmethod
def build_model(cls, args: argparse.Namespace):
- assert check_argument_types()
# 4. Encoder
encoder_class = encoder_choices.get_class(args.encoder)
encoder = encoder_class(**args.encoder_conf)
@@ -291,7 +250,24 @@
model_class = model_choices.get_class(args.model)
except AttributeError:
model_class = model_choices.get_class("e2evad")
- model = model_class(encoder=encoder, vad_post_args=args.vad_post_conf)
+
+ # 1. frontend
+ if args.input_size is None:
+ # Extract features in the model
+ frontend_class = frontend_choices.get_class(args.frontend)
+ if args.frontend == 'wav_frontend':
+ frontend = frontend_class(cmvn_file=args.cmvn_file, **args.frontend_conf)
+ else:
+ frontend = frontend_class(**args.frontend_conf)
+ input_size = frontend.output_size()
+ else:
+ # Give features from data-loader
+ args.frontend = None
+ args.frontend_conf = {}
+ frontend = None
+ input_size = args.input_size
+
+ model = model_class(encoder=encoder, vad_post_args=args.vad_post_conf, frontend=frontend)
return model
@@ -302,6 +278,7 @@
config_file: Union[Path, str] = None,
model_file: Union[Path, str] = None,
device: str = "cpu",
+ cmvn_file: Union[Path, str] = None,
):
"""Build model from the files.
@@ -313,7 +290,6 @@
device: Device type, "cpu", "cuda", or "cuda:N".
"""
- assert check_argument_types()
if config_file is None:
assert model_file is not None, (
"The argument 'model_file' must be provided "
@@ -325,6 +301,8 @@
with config_file.open("r", encoding="utf-8") as f:
args = yaml.safe_load(f)
+ # if cmvn_file is not None:
+ args["cmvn_file"] = cmvn_file
args = argparse.Namespace(**args)
model = cls.build_model(args)
model.to(device)
--
Gitblit v1.9.1