From 4d907718f39e2b0f7a0c714c2e3de289e742fc61 Mon Sep 17 00:00:00 2001
From: Carl <415692979@qq.com>
Date: 星期四, 28 三月 2024 13:42:00 +0800
Subject: [PATCH] 修正commit 87b62d68957a2194b017a43b6c2a15424a05a984 引入的英文整句标点预测导致末尾两个单词中间的空格被删除的问题。 (#1556)
---
funasr/auto/auto_model.py | 12 +++++++-----
1 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index bba44e7..d8ac5ca 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -25,11 +25,12 @@
from funasr.train_utils.set_all_random_seed import set_all_random_seed
from funasr.train_utils.load_pretrained_model import load_pretrained_model
from funasr.utils import export_utils
+
try:
from funasr.models.campplus.utils import sv_chunk, postprocess, distribute_spk
from funasr.models.campplus.cluster_backend import ClusterBackend
except:
- print("Notice: If you want to use the speaker diarization, please `pip install hdbscan`")
+ pass
def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):
@@ -110,7 +111,7 @@
if vad_model is not None:
logging.info("Building VAD model.")
vad_kwargs["model"] = vad_model
- vad_kwargs["model_revision"] = kwargs.get("vad_model_revision", None)
+ vad_kwargs["model_revision"] = kwargs.get("vad_model_revision", "master")
vad_kwargs["device"] = kwargs["device"]
vad_model, vad_kwargs = self.build_model(**vad_kwargs)
@@ -120,7 +121,7 @@
if punc_model is not None:
logging.info("Building punc model.")
punc_kwargs["model"] = punc_model
- punc_kwargs["model_revision"] = kwargs.get("punc_model_revision", None)
+ punc_kwargs["model_revision"] = kwargs.get("punc_model_revision", "master")
punc_kwargs["device"] = kwargs["device"]
punc_model, punc_kwargs = self.build_model(**punc_kwargs)
@@ -130,7 +131,7 @@
if spk_model is not None:
logging.info("Building SPK model.")
spk_kwargs["model"] = spk_model
- spk_kwargs["model_revision"] = kwargs.get("spk_model_revision", None)
+ spk_kwargs["model_revision"] = kwargs.get("spk_model_revision", "master")
spk_kwargs["device"] = kwargs["device"]
spk_model, spk_kwargs = self.build_model(**spk_kwargs)
self.cb_model = ClusterBackend().to(kwargs["device"])
@@ -312,7 +313,8 @@
key = res[i]["key"]
vadsegments = res[i]["value"]
input_i = data_list[i]
- speech = load_audio_text_image_video(input_i, fs=kwargs["frontend"].fs, audio_fs=kwargs.get("fs", 16000))
+ fs = kwargs["frontend"].fs if hasattr(kwargs["frontend"], "fs") else 16000
+ speech = load_audio_text_image_video(input_i, fs=fs, audio_fs=kwargs.get("fs", 16000))
speech_lengths = len(speech)
n = len(vadsegments)
data_with_index = [(vadsegments[i], i) for i in range(n)]
--
Gitblit v1.9.1