From 9be8a443d74d68f179de88fff13b4e8424579d7b Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 10 三月 2023 18:24:39 +0800
Subject: [PATCH] Merge pull request #207 from alibaba-damo-academy/dev_dzh
---
funasr/utils/asr_utils.py | 35 +++++++++++++++++------------------
1 files changed, 17 insertions(+), 18 deletions(-)
diff --git a/funasr/utils/asr_utils.py b/funasr/utils/asr_utils.py
index a6f5ddd..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)
@@ -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'
@@ -128,19 +128,26 @@
def get_sr_from_wav(fname: str):
fs = None
if os.path.isfile(fname):
- audio_type = os.path.basename(fname).split(".")[1].lower()
+ 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)
+ 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)
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):
@@ -158,7 +165,7 @@
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:
@@ -178,7 +185,7 @@
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):
@@ -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