From 429ea5d3786fb77d1b53728307a59fe3d204d4ce Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期三, 15 三月 2023 15:48:35 +0800
Subject: [PATCH] update

---
 funasr/bin/eend_ola_inference.py |    8 +++-----
 1 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/funasr/bin/eend_ola_inference.py b/funasr/bin/eend_ola_inference.py
index d191877..1a47c92 100755
--- a/funasr/bin/eend_ola_inference.py
+++ b/funasr/bin/eend_ola_inference.py
@@ -27,7 +27,6 @@
 from funasr.utils.types import str2triple_str
 from funasr.utils.types import str_or_none
 
-
 class Speech2Diarization:
     """Speech2Diarlization class
 
@@ -121,7 +120,7 @@
                 Currently, the tags of espnet_model_zoo are supported.
 
         Returns:
-            Speech2Xvector: Speech2Xvector instance.
+            Speech2Diarization: Speech2Diarization instance.
 
         """
         if model_tag is not None:
@@ -146,7 +145,7 @@
         output_dir: Optional[str] = None,
         batch_size: int = 1,
         dtype: str = "float32",
-        ngpu: int = 0,
+        ngpu: int = 1,
         num_workers: int = 0,
         log_level: Union[int, str] = "INFO",
         key_file: Optional[str] = None,
@@ -179,7 +178,6 @@
         diar_model_file=diar_model_file,
         device=device,
         dtype=dtype,
-        streaming=streaming,
     )
     logging.info("speech2diarization_kwargs: {}".format(speech2diar_kwargs))
     speech2diar = Speech2Diarization.from_pretrained(
@@ -209,7 +207,7 @@
         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, "speech", "waveform"]
+            data_path_and_name_and_type = [raw_inputs[0], "speech", "bytes"]
         loader = EENDOLADiarTask.build_streaming_iterator(
             data_path_and_name_and_type,
             dtype=dtype,

--
Gitblit v1.9.1