From e6a7bbe1ca6690faa23d29e22cb74a8d67c09ed3 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 05 一月 2024 17:00:11 +0800
Subject: [PATCH] load_audio_text_image_video
---
funasr/models/paraformer/model.py | 13 ++++++++-----
1 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/funasr/models/paraformer/model.py b/funasr/models/paraformer/model.py
index d92d08d..9ee4dfc 100644
--- a/funasr/models/paraformer/model.py
+++ b/funasr/models/paraformer/model.py
@@ -22,7 +22,7 @@
from torch.cuda.amp import autocast
-from funasr.datasets.audio_datasets.load_audio_extract_fbank import load_audio, extract_fbank
+from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter
from funasr.register import tables
@@ -466,7 +466,7 @@
else:
# extract fbank feats
time1 = time.perf_counter()
- audio_sample_list = load_audio(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
+ audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000), data_type=kwargs.get("data_type", "sound"), tokenizer=tokenizer)
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), frontend=frontend)
@@ -495,6 +495,8 @@
results = []
b, n, d = decoder_out.size()
+ if isinstance(key[0], (list, tuple)):
+ key = key[0]
for i in range(b):
x = encoder_out[i, :encoder_out_lens[i], :]
am_scores = decoder_out[i, :pre_token_length[i], :]
@@ -535,13 +537,14 @@
text = tokenizer.tokens2text(token)
text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
- result_i = {"key": key[i], "token": token, "text": text, "text_postprocessed": text_postprocessed}
+
+ result_i = {"key": key[i], "text": text_postprocessed}
if ibest_writer is not None:
ibest_writer["token"][key[i]] = " ".join(token)
- ibest_writer["text"][key[i]] = text
- ibest_writer["text_postprocessed"][key[i]] = text_postprocessed
+ # ibest_writer["text"][key[i]] = text
+ ibest_writer["text"][key[i]] = text_postprocessed
else:
result_i = {"key": key[i], "token_int": token_int}
results.append(result_i)
--
Gitblit v1.9.1