From 65f9d10fdbb65f5a2a85e933906e9d63d1826ed4 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期三, 10 五月 2023 19:32:52 +0800
Subject: [PATCH] update repo
---
funasr/tasks/asr.py | 109 +++++++++++++++++++++++++++++++++++++++++++++++++-----
1 files changed, 98 insertions(+), 11 deletions(-)
diff --git a/funasr/tasks/asr.py b/funasr/tasks/asr.py
index 23ac976..8c8c57e 100644
--- a/funasr/tasks/asr.py
+++ b/funasr/tasks/asr.py
@@ -38,8 +38,9 @@
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 import ASRModel
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
@@ -71,7 +72,7 @@
from funasr.tasks.abs_task import AbsTask
from funasr.text.phoneme_tokenizer import g2p_choices
from funasr.torch_utils.initialize import initialize
-from funasr.train.abs_espnet_model import AbsESPnetModel
+from funasr.models.base_model import FunASRModel
from funasr.train.class_choices import ClassChoices
from funasr.train.trainer import Trainer
from funasr.utils.get_default_kwargs import get_default_kwargs
@@ -117,15 +118,16 @@
model_choices = ClassChoices(
"model",
classes=dict(
- asr=ESPnetASRModel,
+ asr=ASRModel,
uniasr=UniASR,
paraformer=Paraformer,
paraformer_bert=ParaformerBert,
bicif_paraformer=BiCifParaformer,
contextual_paraformer=ContextualParaformer,
mfcca=MFCCA,
+ timestamp_prediction=TimestampPredictor,
),
- type_check=AbsESPnetModel,
+ type_check=FunASRModel,
default="asr",
)
preencoder_choices = ClassChoices(
@@ -438,7 +440,7 @@
token_type=args.token_type,
token_list=args.token_list,
bpemodel=args.bpemodel,
- non_linguistic_symbols=args.non_linguistic_symbols,
+ non_linguistic_symbols=args.non_linguistic_symbols if hasattr(args, "non_linguistic_symbols") else None,
text_cleaner=args.cleaner,
g2p_type=args.g2p,
split_with_space=args.split_with_space if hasattr(args, "split_with_space") else False,
@@ -808,9 +810,9 @@
args["cmvn_file"] = cmvn_file
args = argparse.Namespace(**args)
model = cls.build_model(args)
- if not isinstance(model, AbsESPnetModel):
+ if not isinstance(model, FunASRModel):
raise RuntimeError(
- f"model must inherit {AbsESPnetModel.__name__}, but got {type(model)}"
+ f"model must inherit {FunASRModel.__name__}, but got {type(model)}"
)
model.to(device)
model_dict = dict()
@@ -824,7 +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)
@@ -1055,9 +1057,9 @@
args["cmvn_file"] = cmvn_file
args = argparse.Namespace(**args)
model = cls.build_model(args)
- if not isinstance(model, AbsESPnetModel):
+ if not isinstance(model, FunASRModel):
raise RuntimeError(
- f"model must inherit {AbsESPnetModel.__name__}, but got {type(model)}"
+ f"model must inherit {FunASRModel.__name__}, but got {type(model)}"
)
model.to(device)
model_dict = dict()
@@ -1071,7 +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)
@@ -1244,3 +1246,88 @@
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