From 9b4e9cc8a0311e5243d69b73ed073e7ea441982e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 27 三月 2024 16:05:29 +0800
Subject: [PATCH] train update
---
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