From b1857837dd5873a8308eb770c50f4fc4c8eab752 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期三, 17 一月 2024 16:47:41 +0800
Subject: [PATCH] update
---
funasr/auto/auto_model.py | 9 ++++++---
1 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 580cca8..740614c 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -146,7 +146,7 @@
device = kwargs.get("device", "cuda")
if not torch.cuda.is_available() or kwargs.get("ngpu", 0):
device = "cpu"
- # kwargs["batch_size"] = 1
+ kwargs["batch_size"] = 1
kwargs["device"] = device
if kwargs.get("ncpu", None):
@@ -183,9 +183,11 @@
logging.info(f"Loading pretrained params from {init_param}")
load_pretrained_model(
model=model,
- init_param=init_param,
+ path=init_param,
ignore_init_mismatch=kwargs.get("ignore_init_mismatch", False),
oss_bucket=kwargs.get("oss_bucket", None),
+ scope_map=kwargs.get("scope_map", None),
+ excludes=kwargs.get("excludes", None),
)
return model, kwargs
@@ -307,6 +309,7 @@
time_speech_total_per_sample = speech_lengths/16000
time_speech_total_all_samples += time_speech_total_per_sample
+ all_segments = []
for j, _ in enumerate(range(0, n)):
batch_size_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0])
if j < n - 1 and (
@@ -318,7 +321,7 @@
speech_j, speech_lengths_j = slice_padding_audio_samples(speech, speech_lengths, sorted_data[beg_idx:end_idx])
results = self.inference(speech_j, input_len=None, model=model, kwargs=kwargs, **cfg)
if self.spk_model is not None:
- all_segments = []
+
# compose vad segments: [[start_time_sec, end_time_sec, speech], [...]]
for _b in range(len(speech_j)):
vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0, \
--
Gitblit v1.9.1