From b5d3df75cf6462aa3bf42fd3c86fa2aa7f1c8a15 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 24 十一月 2023 00:54:44 +0800
Subject: [PATCH] setup jamo

---
 funasr/bin/diar_inference_launch.py |   15 ++++++++++++---
 1 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/funasr/bin/diar_inference_launch.py b/funasr/bin/diar_inference_launch.py
index c065137..f5a11b1 100755
--- a/funasr/bin/diar_inference_launch.py
+++ b/funasr/bin/diar_inference_launch.py
@@ -15,7 +15,8 @@
 from typing import Union
 
 import numpy as np
-import soundfile
+# import librosa
+import librosa
 import torch
 from scipy.signal import medfilt
 
@@ -144,7 +145,9 @@
                         # read waveform file
                         example = [load_bytes(x) if isinstance(x, bytes) else x
                                    for x in example]
-                        example = [soundfile.read(x)[0] if isinstance(x, str) else x
+                        # example = [librosa.load(x)[0] if isinstance(x, str) else x
+                        #            for x in example]
+                        example = [librosa.load(x, dtype='float32')[0] if isinstance(x, str) else x
                                    for x in example]
                         # convert torch tensor to numpy array
                         example = [x.numpy() if isinstance(example[0], torch.Tensor) else x
@@ -453,11 +456,17 @@
         help="The batch size for inference",
     )
     group.add_argument(
-        "--diar_smooth_size",
+        "--smooth_size",
         type=int,
         default=121,
         help="The smoothing size for post-processing"
     )
+    group.add_argument(
+        "--dur_threshold",
+        type=int,
+        default=10,
+        help="The threshold of minimum duration"
+    )
 
     return parser
 

--
Gitblit v1.9.1