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