From b0f4910de6dc91c13828026fb5bdd4f15d8636f3 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期二, 27 六月 2023 20:11:30 +0800
Subject: [PATCH] update

---
 funasr/bin/asr_inference_launch.py |   11 ++++++++++-
 1 files changed, 10 insertions(+), 1 deletions(-)

diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 656a965..acc0bc4 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -19,6 +19,7 @@
 import numpy as np
 import torch
 import torchaudio
+import soundfile
 import yaml
 from typeguard import check_argument_types
 
@@ -259,6 +260,7 @@
         export_mode = param_dict.get("export_mode", False)
     else:
         hotword_list_or_file = None
+    clas_scale = param_dict.get('clas_scale', 1.0)
 
     if kwargs.get("device", None) == "cpu":
         ngpu = 0
@@ -291,6 +293,7 @@
         penalty=penalty,
         nbest=nbest,
         hotword_list_or_file=hotword_list_or_file,
+        clas_scale=clas_scale,
     )
 
     speech2text = Speech2TextParaformer(**speech2text_kwargs)
@@ -863,7 +866,13 @@
             raw_inputs = _load_bytes(data_path_and_name_and_type[0])
             raw_inputs = torch.tensor(raw_inputs)
         if data_path_and_name_and_type is not None and data_path_and_name_and_type[2] == "sound":
-            raw_inputs = torchaudio.load(data_path_and_name_and_type[0])[0][0]
+            try:
+                raw_inputs = torchaudio.load(data_path_and_name_and_type[0])[0][0]
+            except:
+                raw_inputs = soundfile.read(data_path_and_name_and_type[0], dtype='float32')[0]
+                if raw_inputs.ndim == 2:
+                    raw_inputs = raw_inputs[:, 0]
+                raw_inputs = torch.tensor(raw_inputs)
         if data_path_and_name_and_type is None and raw_inputs is not None:
             if isinstance(raw_inputs, np.ndarray):
                 raw_inputs = torch.tensor(raw_inputs)

--
Gitblit v1.9.1