From da830cb825edfe55a5a40eddfdd2a5fb8d8e8247 Mon Sep 17 00:00:00 2001
From: lzr265946 <lzr265946@alibaba-inc.com>
Date: 星期五, 24 三月 2023 10:52:59 +0800
Subject: [PATCH] fix uniasr postprocess
---
funasr/tasks/asr.py | 17 +++++++++++------
1 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/funasr/tasks/asr.py b/funasr/tasks/asr.py
index 13898a6..6e0f16a 100644
--- a/funasr/tasks/asr.py
+++ b/funasr/tasks/asr.py
@@ -125,7 +125,7 @@
bicif_paraformer=BiCifParaformer,
contextual_paraformer=ContextualParaformer,
mfcca=MFCCA,
- timestamp_predictor=TimestampPredictor,
+ timestamp_prediction=TimestampPredictor,
),
type_check=AbsESPnetModel,
default="asr",
@@ -411,6 +411,12 @@
type=str,
default="13_15",
help="The range of noise decibel level.",
+ )
+ parser.add_argument(
+ "--batch_interval",
+ type=int,
+ default=10000,
+ help="The batch interval for saving model.",
)
for class_choices in cls.class_choices_list:
@@ -826,7 +832,7 @@
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)
@@ -1073,7 +1079,7 @@
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 +1284,6 @@
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 +1320,7 @@
frontend=frontend,
encoder=encoder,
predictor=predictor,
+ token_list=token_list,
**args.model_conf,
)
@@ -1331,4 +1336,4 @@
cls, train: bool = True, inference: bool = False
) -> Tuple[str, ...]:
retval = ("speech", "text")
- return retval
\ No newline at end of file
+ return retval
--
Gitblit v1.9.1