From d80ac2fd2df4e7fb8a28acfa512bb11472b5cc99 Mon Sep 17 00:00:00 2001
From: liugz18 <57401541+liugz18@users.noreply.github.com>
Date: 星期四, 18 七月 2024 21:34:55 +0800
Subject: [PATCH] Rename 'res' in line 514 to avoid with naming conflict with line 365
---
funasr/auto/auto_model.py | 19 ++++++++++++-------
1 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 1b39e3f..75324dc 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -20,7 +20,7 @@
from funasr.download.file import download_from_url
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.utils.timestamp_tools import timestamp_sentence_en
-from funasr.download.download_from_hub import download_model
+from funasr.download.download_model_from_hub import download_model
from funasr.utils.vad_utils import slice_padding_audio_samples
from funasr.utils.vad_utils import merge_vad
from funasr.utils.load_utils import load_audio_text_image_video
@@ -315,7 +315,7 @@
speed_stats["rtf"] = f"{(time_escape) / batch_data_time:0.3f}"
description = f"{speed_stats}, "
if pbar:
- pbar.update(1)
+ pbar.update(end_idx - beg_idx)
pbar.set_description(description)
time_speech_total += batch_data_time
time_escape_total += time_escape
@@ -339,7 +339,9 @@
# FIX(gcf): concat the vad clips for sense vocie model for better aed
if kwargs.get("merge_vad", False):
for i in range(len(res)):
- res[i]["value"] = merge_vad(res[i]["value"], kwargs.get("merge_length", 15000))
+ res[i]["value"] = merge_vad(
+ res[i]["value"], kwargs.get("merge_length_s", 15) * 1000
+ )
# step.2 compute asr model
model = self.model
@@ -379,6 +381,9 @@
if len(sorted_data) > 0 and len(sorted_data[0]) > 0:
batch_size = max(batch_size, sorted_data[0][0][1] - sorted_data[0][0][0])
+
+ if kwargs["device"] == "cpu":
+ batch_size = 0
beg_idx = 0
beg_asr_total = time.time()
@@ -506,8 +511,8 @@
sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
if self.spk_mode == "vad_segment": # recover sentence_list
sentence_list = []
- for res, vadsegment in zip(restored_data, vadsegments):
- if "timestamp" not in res:
+ for rest, vadsegment in zip(restored_data, vadsegments):
+ if "timestamp" not in rest:
logging.error(
"Only 'iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch' \
and 'iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch'\
@@ -517,8 +522,8 @@
{
"start": vadsegment[0],
"end": vadsegment[1],
- "sentence": res["text"],
- "timestamp": res["timestamp"],
+ "sentence": rest["text"],
+ "timestamp": rest["timestamp"],
}
)
elif self.spk_mode == "punc_segment":
--
Gitblit v1.9.1