From 94de39dde2e616a01683c518023d0fab72b4e103 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 19 二月 2024 22:21:50 +0800
Subject: [PATCH] aishell example
---
funasr/auto/auto_model.py | 17 +++++++++++------
1 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 8007d6e..e95cfd8 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -20,7 +20,10 @@
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.models.campplus.utils import sv_chunk, postprocess, distribute_spk
-from funasr.models.campplus.cluster_backend import ClusterBackend
+try:
+ from funasr.models.campplus.cluster_backend import ClusterBackend
+except:
+ print("If you want to use the speaker diarization, please `pip install hdbscan`")
def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):
@@ -88,7 +91,7 @@
class AutoModel:
def __init__(self, **kwargs):
- if kwargs.get("disable_log", False):
+ if not kwargs.get("disable_log", False):
tables.print()
model, kwargs = self.build_model(**kwargs)
@@ -171,7 +174,7 @@
# build model
model_class = tables.model_classes.get(kwargs["model"])
model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=vocab_size)
- model.eval()
+
model.to(device)
# init_param
@@ -206,6 +209,7 @@
kwargs = self.kwargs if kwargs is None else kwargs
kwargs.update(cfg)
model = self.model if model is None else model
+ model.eval()
batch_size = kwargs.get("batch_size", 1)
# if kwargs.get("device", "cpu") == "cpu":
@@ -385,11 +389,11 @@
result["text"] = punc_res[0]["text"]
# speaker embedding cluster after resorted
- if self.spk_model is not None:
+ if self.spk_model is not None and kwargs.get('return_spk_res', True):
all_segments = sorted(all_segments, key=lambda x: x[0])
spk_embedding = result['spk_embedding']
- labels = self.cb_model(spk_embedding.cpu(), oracle_num=kwargs['preset_spk_num'])
- del result['spk_embedding']
+ labels = self.cb_model(spk_embedding.cpu(), oracle_num=kwargs.get('preset_spk_num', None))
+ # del result['spk_embedding']
sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
if self.spk_mode == 'vad_segment': # recover sentence_list
sentence_list = []
@@ -409,6 +413,7 @@
result['timestamp'], \
result['raw_text'])
result['sentence_info'] = sentence_list
+ del result['spk_embedding']
result["key"] = key
results_ret_list.append(result)
--
Gitblit v1.9.1