From 3f3d00af1f84da17e43746a50d35a51491e30acd Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期三, 14 六月 2023 19:30:48 +0800
Subject: [PATCH] update repo
---
funasr/build_utils/build_asr_model.py | 58 ++++++++++++++++++++++++++--------------------------------
1 files changed, 26 insertions(+), 32 deletions(-)
diff --git a/funasr/build_utils/build_asr_model.py b/funasr/build_utils/build_asr_model.py
index 718736b..e5bed1d 100644
--- a/funasr/build_utils/build_asr_model.py
+++ b/funasr/build_utils/build_asr_model.py
@@ -23,7 +23,7 @@
from funasr.models.joint_net.joint_network import JointNetwork
from funasr.models.e2e_asr import ASRModel
from funasr.models.e2e_asr_mfcca import MFCCA
-from funasr.models.e2e_asr_paraformer import Paraformer, ParaformerBert, BiCifParaformer, ContextualParaformer
+from funasr.models.e2e_asr_paraformer import Paraformer, ParaformerOnline, ParaformerBert, BiCifParaformer, ContextualParaformer
from funasr.models.e2e_tp import TimestampPredictor
from funasr.models.e2e_uni_asr import UniASR
from funasr.models.e2e_asr_transducer import TransducerModel, UnifiedTransducerModel
@@ -82,11 +82,14 @@
asr=ASRModel,
uniasr=UniASR,
paraformer=Paraformer,
+ paraformer_online=ParaformerOnline,
paraformer_bert=ParaformerBert,
bicif_paraformer=BiCifParaformer,
contextual_paraformer=ContextualParaformer,
mfcca=MFCCA,
timestamp_prediction=TimestampPredictor,
+ rnnt=TransducerModel,
+ rnnt_unified=UnifiedTransducerModel,
),
default="asr",
)
@@ -224,17 +227,21 @@
def build_asr_model(args):
# token_list
- if args.token_list is not None:
- with open(args.token_list) as f:
+ if isinstance(args.token_list, str):
+ with open(args.token_list, encoding="utf-8") as f:
token_list = [line.rstrip() for line in f]
args.token_list = list(token_list)
+ vocab_size = len(token_list)
+ logging.info(f"Vocabulary size: {vocab_size}")
+ elif isinstance(args.token_list, (tuple, list)):
+ token_list = list(args.token_list)
vocab_size = len(token_list)
logging.info(f"Vocabulary size: {vocab_size}")
else:
vocab_size = None
# frontend
- if args.input_size is None:
+ if hasattr(args, "input_size") and args.input_size is None:
frontend_class = frontend_choices.get_class(args.frontend)
if args.frontend == 'wav_frontend':
frontend = frontend_class(cmvn_file=args.cmvn_file, **args.frontend_conf)
@@ -291,7 +298,7 @@
token_list=token_list,
**args.model_conf,
)
- elif args.model in ["paraformer", "paraformer_bert", "bicif_paraformer", "contextual_paraformer"]:
+ elif args.model in ["paraformer", "paraformer_online", "paraformer_bert", "bicif_paraformer", "contextual_paraformer"]:
# predictor
predictor_class = predictor_choices.get_class(args.predictor)
predictor = predictor_class(**args.predictor_conf)
@@ -367,7 +374,7 @@
token_list=token_list,
**args.model_conf,
)
- elif args.model == "rnnt":
+ elif args.model == "rnnt" or args.model == "rnnt_unified":
# 5. Decoder
encoder_output_size = encoder.output_size()
@@ -396,34 +403,21 @@
**args.joint_network_conf,
)
+ model_class = model_choices.get_class(args.model)
# 7. Build model
- if hasattr(encoder, 'unified_model_training') and encoder.unified_model_training:
- model = UnifiedTransducerModel(
- vocab_size=vocab_size,
- token_list=token_list,
- frontend=frontend,
- specaug=specaug,
- normalize=normalize,
- encoder=encoder,
- decoder=decoder,
- att_decoder=att_decoder,
- joint_network=joint_network,
- **args.model_conf,
- )
+ model = model_class(
+ vocab_size=vocab_size,
+ token_list=token_list,
+ frontend=frontend,
+ specaug=specaug,
+ normalize=normalize,
+ encoder=encoder,
+ decoder=decoder,
+ att_decoder=att_decoder,
+ joint_network=joint_network,
+ **args.model_conf,
+ )
- else:
- model = TransducerModel(
- vocab_size=vocab_size,
- token_list=token_list,
- frontend=frontend,
- specaug=specaug,
- normalize=normalize,
- encoder=encoder,
- decoder=decoder,
- att_decoder=att_decoder,
- joint_network=joint_network,
- **args.model_conf,
- )
else:
raise NotImplementedError("Not supported model: {}".format(args.model))
--
Gitblit v1.9.1