From d783b24ba7d8a03dabfa2139fcbf40c216e0ea3d Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 三月 2023 19:34:52 +0800
Subject: [PATCH] Merge pull request #199 from alibaba-damo-academy/dev_xw
---
funasr/utils/asr_utils.py | 25 ++++++++++++-------------
1 files changed, 12 insertions(+), 13 deletions(-)
diff --git a/funasr/utils/asr_utils.py b/funasr/utils/asr_utils.py
index 76b20a5..0f0e4c3 100644
--- a/funasr/utils/asr_utils.py
+++ b/funasr/utils/asr_utils.py
@@ -27,7 +27,7 @@
def sample_rate_checking(audio_in: Union[str, bytes], audio_format: str):
r_audio_fs = None
- if audio_format == 'wav':
+ if audio_format == 'wav' or audio_format == 'scp':
r_audio_fs = get_sr_from_wav(audio_in)
elif audio_format == 'pcm' and isinstance(audio_in, bytes):
r_audio_fs = get_sr_from_bytes(audio_in)
@@ -134,6 +134,13 @@
fs = None
else:
audio, fs = torchaudio.load(fname)
+ elif audio_type == "scp":
+ with open(fname, encoding="utf-8") as f:
+ for line in f:
+ wav_path = line.split()[1]
+ fs = get_sr_from_wav(wav_path)
+ if fs is not None:
+ break
return fs
elif os.path.isdir(fname):
dir_files = os.listdir(fname)
@@ -186,22 +193,11 @@
return wav_list
-
-def set_parameters(language: str = None):
- if language is not None:
- global global_asr_language
- global_asr_language = language
-
-
def compute_wer(hyp_list: List[Any],
ref_list: List[Any],
lang: str = None) -> Dict[str, Any]:
assert len(hyp_list) > 0, 'hyp list is empty'
assert len(ref_list) > 0, 'ref list is empty'
-
- if lang is not None:
- global global_asr_language
- global_asr_language = lang
rst = {
'Wrd': 0,
@@ -216,12 +212,15 @@
'wrong_sentences': 0
}
+ if lang is None:
+ lang = global_asr_language
+
for h_item in hyp_list:
for r_item in ref_list:
if h_item['key'] == r_item['key']:
out_item = compute_wer_by_line(h_item['value'],
r_item['value'],
- global_asr_language)
+ lang)
rst['Wrd'] += out_item['nwords']
rst['Corr'] += out_item['cor']
rst['wrong_words'] += out_item['wrong']
--
Gitblit v1.9.1