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 | 36 +++++++++++++-----------------------
1 files changed, 13 insertions(+), 23 deletions(-)
diff --git a/funasr/tasks/asr.py b/funasr/tasks/asr.py
index 05eace7..8c8c57e 100644
--- a/funasr/tasks/asr.py
+++ b/funasr/tasks/asr.py
@@ -38,7 +38,7 @@
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
@@ -72,7 +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
@@ -118,16 +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_predictor=TimestampPredictor,
+ timestamp_prediction=TimestampPredictor,
),
- type_check=AbsESPnetModel,
+ type_check=FunASRModel,
default="asr",
)
preencoder_choices = ClassChoices(
@@ -440,7 +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,
@@ -810,9 +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()
@@ -826,7 +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)
@@ -1057,9 +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()
@@ -1073,7 +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)
@@ -1278,8 +1278,6 @@
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:
@@ -1316,6 +1314,7 @@
frontend=frontend,
encoder=encoder,
predictor=predictor,
+ token_list=token_list,
**args.model_conf,
)
@@ -1332,12 +1331,3 @@
) -> Tuple[str, ...]:
retval = ("speech", "text")
return retval
-
-
-class ASRTaskAligner(ASRTaskParaformer):
- @classmethod
- def required_data_names(
- cls, train: bool = True, inference: bool = False
- ) -> Tuple[str, ...]:
- retval = ("speech", "text")
- return retval
\ No newline at end of file
--
Gitblit v1.9.1