From 6d7b9457103264b760f79918aa13ec1b89474670 Mon Sep 17 00:00:00 2001
From: 语帆 <yf352572@alibaba-inc.com>
Date: 星期五, 01 三月 2024 11:10:44 +0800
Subject: [PATCH] atsr
---
funasr/auto/auto_model.py | 2 +-
funasr/models/lcbnet/model.py | 3 ++-
funasr/utils/load_utils.py | 4 ++--
3 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 56dd5b5..9bb9ce0 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -41,7 +41,7 @@
chars = string.ascii_letters + string.digits
if isinstance(data_in, str) and data_in.startswith('http'): # url
data_in = download_from_url(data_in)
- pdb.set_trace()
+
if isinstance(data_in, str) and os.path.exists(data_in): # wav_path; filelist: wav.scp, file.jsonl;text.txt;
_, file_extension = os.path.splitext(data_in)
file_extension = file_extension.lower()
diff --git a/funasr/models/lcbnet/model.py b/funasr/models/lcbnet/model.py
index ab557e6..09e6dd1 100644
--- a/funasr/models/lcbnet/model.py
+++ b/funasr/models/lcbnet/model.py
@@ -426,6 +426,7 @@
tokenizer=tokenizer)
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
+ pdb.set_trace()
audio_sample_list = sample_list[0]
ocr_sample_list = sample_list[1]
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
@@ -441,7 +442,7 @@
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
if isinstance(encoder_out, tuple):
encoder_out = encoder_out[0]
-
+ pdb.set_trace()
ocr_list_new = [[x + 1 if x != 0 else x for x in sublist] for sublist in ocr_sample_list]
ocr = torch.tensor(ocr_list_new).to(device=kwargs["device"])
ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1)).to(device=kwargs["device"])
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.py
index ccb5670..644af23 100644
--- a/funasr/utils/load_utils.py
+++ b/funasr/utils/load_utils.py
@@ -31,7 +31,7 @@
return [load_audio_text_image_video(audio, fs=fs, audio_fs=audio_fs, data_type=data_type, **kwargs) for audio in data_or_path_or_list]
if isinstance(data_or_path_or_list, str) and data_or_path_or_list.startswith('http'): # download url to local file
data_or_path_or_list = download_from_url(data_or_path_or_list)
- pdb.set_trace()
+
if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local file
if data_type is None or data_type == "sound":
data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list)
@@ -67,7 +67,7 @@
else:
pass
# print(f"unsupport data type: {data_or_path_or_list}, return raw data")
- pdb.set_trace()
+
if audio_fs != fs and data_type != "text":
resampler = torchaudio.transforms.Resample(audio_fs, fs)
data_or_path_or_list = resampler(data_or_path_or_list[None, :])[0, :]
--
Gitblit v1.9.1