From 93a02feda1848531a48a1794a8de12a962c84a8e Mon Sep 17 00:00:00 2001
From: Xingchen Song(宋星辰) <xingchensong1996@163.com>
Date: 星期五, 07 六月 2024 23:10:13 +0800
Subject: [PATCH] [fix] fix empty asr result (#1794)
---
funasr/auto/auto_model.py | 11 +++++++----
1 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 97eb325..9b4f6d9 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -42,8 +42,9 @@
filelist = [".scp", ".txt", ".json", ".jsonl", ".text"]
chars = string.ascii_letters + string.digits
- if isinstance(data_in, str) and data_in.startswith("http"): # url
- data_in = download_from_url(data_in)
+ if isinstance(data_in, str):
+ if data_in.startswith("http://") or data_in.startswith("https://"): # url
+ data_in = download_from_url(data_in)
if isinstance(data_in, str) and os.path.exists(
data_in
@@ -284,7 +285,7 @@
with torch.no_grad():
res = model.inference(**batch, **kwargs)
if isinstance(res, (list, tuple)):
- results = res[0]
+ results = res[0] if len(res) > 0 else [{"text": ""}]
meta_data = res[1] if len(res) > 1 else {}
time2 = time.perf_counter()
@@ -358,6 +359,7 @@
results_sorted = []
if not len(sorted_data):
+ results_ret_list.append({"key": key, "text": "", "timestamp": []})
logging.info("decoding, utt: {}, empty speech".format(key))
continue
@@ -386,6 +388,7 @@
):
max_len_in_batch = max(max_len_in_batch, sample_length)
end_idx += 1
+ results_sorted.append({'key': 'bad_data', 'text': '', 'timestamp': []})
continue
speech_j, speech_lengths_j = slice_padding_audio_samples(
@@ -415,7 +418,7 @@
end_idx += 1
max_len_in_batch = sample_length
if len(results) < 1:
- continue
+ results.append({'key': 'bad_data', 'text': '', 'timestamp': []})
results_sorted.extend(results)
# end_asr_total = time.time()
--
Gitblit v1.9.1