From fdf74bb85cfe3dd0ce6cbaf51ec8d5b3ca3d2039 Mon Sep 17 00:00:00 2001
From: 仁迷 <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 09 二月 2023 17:18:43 +0800
Subject: [PATCH] update persian model recipe
---
funasr/utils/asr_utils.py | 18 +++++++++++-------
1 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/funasr/utils/asr_utils.py b/funasr/utils/asr_utils.py
index aa5c9db..76b20a5 100644
--- a/funasr/utils/asr_utils.py
+++ b/funasr/utils/asr_utils.py
@@ -18,7 +18,7 @@
global_asr_language = 'zh-cn'
-SUPPORT_AUDIO_TYPE_SETS = ['flac', 'mp3', 'm4a', 'ogg', 'opus', 'wav', 'wma']
+SUPPORT_AUDIO_TYPE_SETS = ['flac', 'mp3', 'ogg', 'opus', 'wav', 'pcm']
def get_version():
return float(pkg_resources.get_distribution('easyasr').version)
@@ -58,7 +58,7 @@
if r_recog_type is None and audio_in is not None:
# audio_in is wav, recog_type is wav_file
if os.path.isfile(audio_in):
- audio_type = os.path.basename(audio_in).split(".")[1].lower()
+ audio_type = os.path.basename(audio_in).split(".")[-1].lower()
if audio_type in SUPPORT_AUDIO_TYPE_SETS:
r_recog_type = 'wav'
r_audio_format = 'wav'
@@ -128,14 +128,19 @@
def get_sr_from_wav(fname: str):
fs = None
if os.path.isfile(fname):
- audio, fs = torchaudio.load(fname)
+ audio_type = os.path.basename(fname).split(".")[-1].lower()
+ if audio_type in SUPPORT_AUDIO_TYPE_SETS:
+ if audio_type == "pcm":
+ fs = None
+ else:
+ audio, fs = torchaudio.load(fname)
return fs
elif os.path.isdir(fname):
dir_files = os.listdir(fname)
for file in dir_files:
file_path = os.path.join(fname, file)
if os.path.isfile(file_path):
- audio_type = os.path.basename(file_path).split(".")[1].lower()
+ audio_type = os.path.basename(file_path).split(".")[-1].lower()
if audio_type in SUPPORT_AUDIO_TYPE_SETS:
fs = get_sr_from_wav(file_path)
elif os.path.isdir(file_path):
@@ -153,7 +158,7 @@
file_path = os.path.join(dir_path, file)
if os.path.isfile(file_path):
if ends == ".wav" or ends == ".WAV":
- audio_type = os.path.basename(file_path).split(".")[1].lower()
+ audio_type = os.path.basename(file_path).split(".")[-1].lower()
if audio_type in SUPPORT_AUDIO_TYPE_SETS:
return True
else:
@@ -173,7 +178,7 @@
for file in dir_files:
file_path = os.path.join(dir_path, file)
if os.path.isfile(file_path):
- audio_type = os.path.basename(file_path).split(".")[1].lower()
+ audio_type = os.path.basename(file_path).split(".")[-1].lower()
if audio_type in SUPPORT_AUDIO_TYPE_SETS:
wav_list.append(file_path)
elif os.path.isdir(file_path):
@@ -347,4 +352,3 @@
percent = 1
res = int(50 * percent) * '#'
print('\r[%-50s] %d%%' % (res, int(100 * percent)), end='')
-
--
Gitblit v1.9.1