From 566242c94bbe596fa92c347d5a0cd63b44d54e35 Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期五, 03 二月 2023 11:03:56 +0800
Subject: [PATCH] Merge branch 'dev' of https://github.com/alibaba-damo-academy/FunASR into dev
---
funasr/bin/asr_inference_paraformer_vad_punc.py | 25 +++++++++++++++++++------
1 files changed, 19 insertions(+), 6 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_vad_punc.py b/funasr/bin/asr_inference_paraformer_vad_punc.py
index 4b5b316..eec2aaa 100644
--- a/funasr/bin/asr_inference_paraformer_vad_punc.py
+++ b/funasr/bin/asr_inference_paraformer_vad_punc.py
@@ -3,6 +3,7 @@
import logging
import sys
import time
+import json
from pathlib import Path
from typing import Optional
from typing import Sequence
@@ -100,10 +101,13 @@
# logging.info("asr_train_args: {}".format(asr_train_args))
asr_model.to(dtype=getattr(torch, dtype)).eval()
- ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
+ if asr_model.ctc != None:
+ ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
+ scorers.update(
+ ctc=ctc
+ )
token_list = asr_model.token_list
scorers.update(
- ctc=ctc,
length_bonus=LengthBonus(len(token_list)),
)
@@ -171,7 +175,7 @@
self.converter = converter
self.tokenizer = tokenizer
is_use_lm = lm_weight != 0.0 and lm_file is not None
- if ctc_weight == 0.0 and not is_use_lm:
+ if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
beam_search = None
self.beam_search = beam_search
logging.info(f"Beam_search: {self.beam_search}")
@@ -475,6 +479,7 @@
punc_infer_config: Optional[str] = None,
punc_model_file: Optional[str] = None,
outputs_dict: Optional[bool] = True,
+ param_dict: dict = None,
**kwargs,
):
assert check_argument_types()
@@ -540,6 +545,7 @@
def _forward(data_path_and_name_and_type,
raw_inputs: Union[np.ndarray, torch.Tensor] = None,
output_dir_v2: Optional[str] = None,
+ param_dict: dict = None,
):
# 3. Build data-iterator
if data_path_and_name_and_type is None and raw_inputs is not None:
@@ -632,9 +638,16 @@
text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], \
postprocessed_result[1], \
postprocessed_result[2]
- text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
- text_postprocessed_punc_time_stamp = "predictions: {} time_stamp: {}".format(
- text_postprocessed_punc, time_stamp_postprocessed)
+ if len(word_lists) > 0:
+ text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
+ text_postprocessed_punc_time_stamp = json.dumps({"predictions": text_postprocessed_punc,
+ "time_stamp": time_stamp_postprocessed},
+ ensure_ascii=False)
+ else:
+ text_postprocessed_punc = ""
+ punc_id_list = []
+ text_postprocessed_punc_time_stamp = ""
+
else:
text_postprocessed = ""
time_stamp_postprocessed = ""
--
Gitblit v1.9.1