From c3867c850182abaab1596dbe20ac8aba2df8f5c6 Mon Sep 17 00:00:00 2001
From: lingyunfly <121302812+lingyunfly@users.noreply.github.com>
Date: 星期二, 14 三月 2023 13:18:36 +0800
Subject: [PATCH] Update infer_online.py
---
funasr/bin/asr_inference_mfcca.py | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/funasr/bin/asr_inference_mfcca.py b/funasr/bin/asr_inference_mfcca.py
index e25b2a9..4176ba6 100644
--- a/funasr/bin/asr_inference_mfcca.py
+++ b/funasr/bin/asr_inference_mfcca.py
@@ -194,8 +194,8 @@
# Input as audio signal
if isinstance(speech, np.ndarray):
speech = torch.tensor(speech)
-
-
+ if(speech.dim()==3):
+ speech = torch.squeeze(speech, 2)
#speech = speech.unsqueeze(0).to(getattr(torch, self.dtype))
speech = speech.to(getattr(torch, self.dtype))
# lenghts: (1,)
@@ -534,6 +534,8 @@
data_path_and_name_and_type,
dtype=dtype,
batch_size=batch_size,
+ fs=fs,
+ mc=True,
key_file=key_file,
num_workers=num_workers,
preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
--
Gitblit v1.9.1