From fb176404cfeb40c053f4f42d01eb45c185d21ce2 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 08 一月 2024 16:20:45 +0800
Subject: [PATCH] funasr1.0 emotion2vec
---
funasr/bin/inference.py | 9 +++++----
1 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/funasr/bin/inference.py b/funasr/bin/inference.py
index be7cf88..5b58907 100644
--- a/funasr/bin/inference.py
+++ b/funasr/bin/inference.py
@@ -17,7 +17,7 @@
import string
from funasr.register import tables
-from funasr.utils.load_utils import load_audio_and_text_image_video, extract_fbank
+from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils.vad_utils import slice_padding_audio_samples
from funasr.utils.timestamp_tools import time_stamp_sentence
@@ -222,7 +222,8 @@
batch["data_lengths"] = input_len
time1 = time.perf_counter()
- results, meta_data = model.generate(**batch, **kwargs)
+ with torch.no_grad():
+ results, meta_data = model.generate(**batch, **kwargs)
time2 = time.perf_counter()
asr_result_list.extend(results)
@@ -278,7 +279,7 @@
key = res[i]["key"]
vadsegments = res[i]["value"]
input_i = data_list[i]
- speech = load_audio_and_text_image_video(input_i, fs=kwargs["frontend"].fs, audio_fs=kwargs.get("fs", 16000))
+ speech = load_audio_text_image_video(input_i, fs=kwargs["frontend"].fs, audio_fs=kwargs.get("fs", 16000))
speech_lengths = len(speech)
n = len(vadsegments)
data_with_index = [(vadsegments[i], i) for i in range(n)]
@@ -417,7 +418,7 @@
# extract fbank feats
time1 = time.perf_counter()
- audio_sample_list = load_audio_and_text_image_video(data_batch, fs=self.frontend.fs, audio_fs=kwargs.get("fs", 16000))
+ audio_sample_list = load_audio_text_image_video(data_batch, fs=self.frontend.fs, audio_fs=kwargs.get("fs", 16000))
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"),
--
Gitblit v1.9.1