From fa3e8359835107aa9ab8e3ae604ed61cad407bf8 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 14 六月 2024 10:38:02 +0800
Subject: [PATCH] update with main (#1816)
---
funasr/auto/auto_model.py | 43 ++++++++++++++++++++++++++++++-------------
1 files changed, 30 insertions(+), 13 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index bbaf657..e30eb09 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -19,6 +19,7 @@
from funasr.utils.load_utils import load_bytes
from funasr.download.file import download_from_url
from funasr.utils.timestamp_tools import timestamp_sentence
+from funasr.utils.timestamp_tools import timestamp_sentence_en
from funasr.download.download_from_hub import download_model
from funasr.utils.vad_utils import slice_padding_audio_samples
from funasr.utils.vad_utils import merge_vad
@@ -323,7 +324,7 @@
input, input_len=input_len, model=self.vad_model, kwargs=self.vad_kwargs, **cfg
)
end_vad = time.time()
-
+
# FIX(gcf): concat the vad clips for sense vocie model for better aed
if kwargs.get("merge_vad", False):
for i in range(len(res)):
@@ -519,24 +520,40 @@
and 'iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch'\
can predict timestamp, and speaker diarization relies on timestamps."
)
- sentence_list = timestamp_sentence(
- punc_res[0]["punc_array"],
- result["timestamp"],
- raw_text,
- return_raw_text=return_raw_text,
- )
+ if kwargs.get("en_post_proc", False):
+ sentence_list = timestamp_sentence_en(
+ punc_res[0]["punc_array"],
+ result["timestamp"],
+ raw_text,
+ return_raw_text=return_raw_text,
+ )
+ else:
+ sentence_list = timestamp_sentence(
+ punc_res[0]["punc_array"],
+ result["timestamp"],
+ raw_text,
+ return_raw_text=return_raw_text,
+ )
distribute_spk(sentence_list, sv_output)
result["sentence_info"] = sentence_list
elif kwargs.get("sentence_timestamp", False):
if not len(result["text"].strip()):
sentence_list = []
else:
- sentence_list = timestamp_sentence(
- punc_res[0]["punc_array"],
- result["timestamp"],
- raw_text,
- return_raw_text=return_raw_text,
- )
+ if kwargs.get("en_post_proc", False):
+ sentence_list = timestamp_sentence_en(
+ punc_res[0]["punc_array"],
+ result["timestamp"],
+ raw_text,
+ return_raw_text=return_raw_text,
+ )
+ else:
+ sentence_list = timestamp_sentence(
+ punc_res[0]["punc_array"],
+ result["timestamp"],
+ raw_text,
+ return_raw_text=return_raw_text,
+ )
result["sentence_info"] = sentence_list
if "spk_embedding" in result:
del result["spk_embedding"]
--
Gitblit v1.9.1