From 28a19dbc4e85d3b8a4ec2ef7483bba64d422b43f Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期三, 12 四月 2023 18:03:06 +0800
Subject: [PATCH] Merge remote-tracking branch 'origin/main' into dev_aky
---
funasr/tasks/asr.py | 237 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 234 insertions(+), 3 deletions(-)
diff --git a/funasr/tasks/asr.py b/funasr/tasks/asr.py
index 1b7f152..e151473 100644
--- a/funasr/tasks/asr.py
+++ b/funasr/tasks/asr.py
@@ -37,8 +37,11 @@
)
from funasr.models.decoder.transformer_decoder import ParaformerDecoderSAN
from funasr.models.decoder.transformer_decoder import TransformerDecoder
+from funasr.models.decoder.contextual_decoder import ContextualParaformerDecoder
from funasr.models.e2e_asr import ESPnetASRModel
-from funasr.models.e2e_asr_paraformer import Paraformer, ParaformerBert, BiCifParaformer
+from funasr.models.e2e_asr_paraformer import Paraformer, ParaformerBert, BiCifParaformer, ContextualParaformer
+from funasr.models.e2e_tp import TimestampPredictor
+from funasr.models.e2e_asr_mfcca import MFCCA
from funasr.models.e2e_uni_asr import UniASR
from funasr.models.encoder.abs_encoder import AbsEncoder
from funasr.models.encoder.conformer_encoder import ConformerEncoder
@@ -46,8 +49,10 @@
from funasr.models.encoder.rnn_encoder import RNNEncoder
from funasr.models.encoder.sanm_encoder import SANMEncoder, SANMEncoderChunkOpt
from funasr.models.encoder.transformer_encoder import TransformerEncoder
+from funasr.models.encoder.mfcca_encoder import MFCCAEncoder
from funasr.models.frontend.abs_frontend import AbsFrontend
from funasr.models.frontend.default import DefaultFrontend
+from funasr.models.frontend.default import MultiChannelFrontend
from funasr.models.frontend.fused import FusedFrontends
from funasr.models.frontend.s3prl import S3prlFrontend
from funasr.models.frontend.wav_frontend import WavFrontend
@@ -85,6 +90,7 @@
s3prl=S3prlFrontend,
fused=FusedFrontends,
wav_frontend=WavFrontend,
+ multichannelfrontend=MultiChannelFrontend,
),
type_check=AbsFrontend,
default="default",
@@ -117,6 +123,9 @@
paraformer=Paraformer,
paraformer_bert=ParaformerBert,
bicif_paraformer=BiCifParaformer,
+ contextual_paraformer=ContextualParaformer,
+ mfcca=MFCCA,
+ timestamp_prediction=TimestampPredictor,
),
type_check=AbsESPnetModel,
default="asr",
@@ -140,6 +149,7 @@
sanm=SANMEncoder,
sanm_chunk_opt=SANMEncoderChunkOpt,
data2vec_encoder=Data2VecEncoder,
+ mfcca_enc=MFCCAEncoder,
),
type_check=AbsEncoder,
default="rnn",
@@ -177,6 +187,7 @@
fsmn_scama_opt=FsmnDecoderSCAMAOpt,
paraformer_decoder_sanm=ParaformerSANMDecoder,
paraformer_decoder_san=ParaformerDecoderSAN,
+ contextual_paraformer_decoder=ContextualParaformerDecoder,
),
type_check=AbsDecoder,
default="rnn",
@@ -815,7 +826,7 @@
if "model.ckpt-" in model_name or ".bin" in model_name:
model_name_pth = os.path.join(model_dir, model_name.replace('.bin',
'.pb')) if ".bin" in model_name else os.path.join(
- model_dir, "{}.pth".format(model_name))
+ model_dir, "{}.pb".format(model_name))
if os.path.exists(model_name_pth):
logging.info("model_file is load from pth: {}".format(model_name_pth))
model_dict = torch.load(model_name_pth, map_location=device)
@@ -1062,7 +1073,7 @@
if "model.ckpt-" in model_name or ".bin" in model_name:
model_name_pth = os.path.join(model_dir, model_name.replace('.bin',
'.pb')) if ".bin" in model_name else os.path.join(
- model_dir, "{}.pth".format(model_name))
+ model_dir, "{}.pb".format(model_name))
if os.path.exists(model_name_pth):
logging.info("model_file is load from pth: {}".format(model_name_pth))
model_dict = torch.load(model_name_pth, map_location=device)
@@ -1098,5 +1109,225 @@
# decoder
var_dict_torch_update_local = model.decoder.convert_tf2torch(var_dict_tf, var_dict_torch)
var_dict_torch_update.update(var_dict_torch_update_local)
+ # bias_encoder
+ var_dict_torch_update_local = model.clas_convert_tf2torch(var_dict_tf, var_dict_torch)
+ var_dict_torch_update.update(var_dict_torch_update_local)
return var_dict_torch_update
+
+
+
+class ASRTaskMFCCA(ASRTask):
+ # If you need more than one optimizers, change this value
+ num_optimizers: int = 1
+
+ # Add variable objects configurations
+ class_choices_list = [
+ # --frontend and --frontend_conf
+ frontend_choices,
+ # --specaug and --specaug_conf
+ specaug_choices,
+ # --normalize and --normalize_conf
+ normalize_choices,
+ # --model and --model_conf
+ model_choices,
+ # --preencoder and --preencoder_conf
+ preencoder_choices,
+ # --encoder and --encoder_conf
+ encoder_choices,
+ # --decoder and --decoder_conf
+ decoder_choices,
+ ]
+
+ # If you need to modify train() or eval() procedures, change Trainer class here
+ trainer = Trainer
+
+ @classmethod
+ def build_model(cls, args: argparse.Namespace):
+ assert check_argument_types()
+ if isinstance(args.token_list, str):
+ with open(args.token_list, encoding="utf-8") as f:
+ token_list = [line.rstrip() for line in f]
+
+ # Overwriting token_list to keep it as "portable".
+ args.token_list = list(token_list)
+ elif isinstance(args.token_list, (tuple, list)):
+ token_list = list(args.token_list)
+ else:
+ raise RuntimeError("token_list must be str or list")
+ vocab_size = len(token_list)
+ logging.info(f"Vocabulary size: {vocab_size}")
+
+ # 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
+
+ # 2. Data augmentation for spectrogram
+ if args.specaug is not None:
+ specaug_class = specaug_choices.get_class(args.specaug)
+ specaug = specaug_class(**args.specaug_conf)
+ else:
+ specaug = None
+
+ # 3. Normalization layer
+ if args.normalize is not None:
+ normalize_class = normalize_choices.get_class(args.normalize)
+ normalize = normalize_class(stats_file=args.cmvn_file,**args.normalize_conf)
+ else:
+ normalize = None
+
+ # 4. Pre-encoder input block
+ # NOTE(kan-bayashi): Use getattr to keep the compatibility
+ if getattr(args, "preencoder", None) is not None:
+ preencoder_class = preencoder_choices.get_class(args.preencoder)
+ preencoder = preencoder_class(**args.preencoder_conf)
+ input_size = preencoder.output_size()
+ else:
+ preencoder = None
+
+ # 5. Encoder
+ encoder_class = encoder_choices.get_class(args.encoder)
+ encoder = encoder_class(input_size=input_size, **args.encoder_conf)
+
+ # 7. Decoder
+ decoder_class = decoder_choices.get_class(args.decoder)
+ decoder = decoder_class(
+ vocab_size=vocab_size,
+ encoder_output_size=encoder.output_size(),
+ **args.decoder_conf,
+ )
+
+ # 8. CTC
+ ctc = CTC(
+ odim=vocab_size, encoder_output_size=encoder.output_size(), **args.ctc_conf
+ )
+
+
+ # 10. Build model
+ try:
+ model_class = model_choices.get_class(args.model)
+ except AttributeError:
+ model_class = model_choices.get_class("asr")
+
+ rnnt_decoder = None
+
+ # 8. Build model
+ model = model_class(
+ vocab_size=vocab_size,
+ frontend=frontend,
+ specaug=specaug,
+ normalize=normalize,
+ preencoder=preencoder,
+ encoder=encoder,
+ decoder=decoder,
+ ctc=ctc,
+ rnnt_decoder=rnnt_decoder,
+ token_list=token_list,
+ **args.model_conf,
+ )
+
+ # 11. Initialize
+ if args.init is not None:
+ initialize(model, args.init)
+
+ assert check_return_type(model)
+ return model
+
+
+class ASRTaskAligner(ASRTaskParaformer):
+ # If you need more than one optimizers, change this value
+ num_optimizers: int = 1
+
+ # Add variable objects configurations
+ class_choices_list = [
+ # --frontend and --frontend_conf
+ frontend_choices,
+ # --model and --model_conf
+ model_choices,
+ # --encoder and --encoder_conf
+ encoder_choices,
+ # --decoder and --decoder_conf
+ decoder_choices,
+ ]
+
+ # If you need to modify train() or eval() procedures, change Trainer class here
+ trainer = Trainer
+
+ @classmethod
+ def build_model(cls, args: argparse.Namespace):
+ assert check_argument_types()
+ if isinstance(args.token_list, str):
+ with open(args.token_list, encoding="utf-8") as f:
+ token_list = [line.rstrip() for line in f]
+
+ # Overwriting token_list to keep it as "portable".
+ args.token_list = list(token_list)
+ elif isinstance(args.token_list, (tuple, list)):
+ token_list = list(args.token_list)
+ else:
+ raise RuntimeError("token_list must be str or list")
+
+ # 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
+
+ # 2. Encoder
+ encoder_class = encoder_choices.get_class(args.encoder)
+ encoder = encoder_class(input_size=input_size, **args.encoder_conf)
+
+ # 3. Predictor
+ predictor_class = predictor_choices.get_class(args.predictor)
+ predictor = predictor_class(**args.predictor_conf)
+
+ # 10. Build model
+ try:
+ model_class = model_choices.get_class(args.model)
+ except AttributeError:
+ model_class = model_choices.get_class("asr")
+
+ # 8. Build model
+ model = model_class(
+ frontend=frontend,
+ encoder=encoder,
+ predictor=predictor,
+ token_list=token_list,
+ **args.model_conf,
+ )
+
+ # 11. Initialize
+ if args.init is not None:
+ initialize(model, args.init)
+
+ assert check_return_type(model)
+ return model
+
+ @classmethod
+ def required_data_names(
+ cls, train: bool = True, inference: bool = False
+ ) -> Tuple[str, ...]:
+ retval = ("speech", "text")
+ return retval
--
Gitblit v1.9.1