From c3bce4c288f73a3bbf5559b019d4480f95acffaa Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 16 三月 2023 10:44:15 +0800
Subject: [PATCH] update

---
 funasr/modules/eend_ola/encoder.py |    2 +-
 setup.py                           |    2 +-
 funasr/bin/eend_ola_inference.py   |    2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/funasr/bin/eend_ola_inference.py b/funasr/bin/eend_ola_inference.py
index 0483278..bc29fa2 100755
--- a/funasr/bin/eend_ola_inference.py
+++ b/funasr/bin/eend_ola_inference.py
@@ -209,7 +209,7 @@
         if data_path_and_name_and_type is None and raw_inputs is not None:
             if isinstance(raw_inputs, torch.Tensor):
                 raw_inputs = raw_inputs.numpy()
-            data_path_and_name_and_type = [raw_inputs[0], "speech", "bytes"]
+            data_path_and_name_and_type = [raw_inputs[0], "speech", "sound"]
         loader = EENDOLADiarTask.build_streaming_iterator(
             data_path_and_name_and_type,
             dtype=dtype,
diff --git a/funasr/modules/eend_ola/encoder.py b/funasr/modules/eend_ola/encoder.py
index 4999031..90a63f3 100644
--- a/funasr/modules/eend_ola/encoder.py
+++ b/funasr/modules/eend_ola/encoder.py
@@ -87,7 +87,7 @@
                  n_layers: int,
                  n_units: int,
                  e_units: int = 2048,
-                 h: int = 8,
+                 h: int = 4,
                  dropout_rate: float = 0.1,
                  use_pos_emb: bool = False):
         super(EENDOLATransformerEncoder, self).__init__()
diff --git a/setup.py b/setup.py
index 087d90d..e6b9d38 100644
--- a/setup.py
+++ b/setup.py
@@ -17,7 +17,7 @@
         "humanfriendly",
         "scipy>=1.4.1",
         # "filelock",
-        "librosa>=0.8.0",
+        "librosa==0.8.1",
         "jamo==0.4.1",  # For kss
         "PyYAML>=5.1.2",
         "soundfile>=0.10.2",

--
Gitblit v1.9.1