From 4ace5a95b052d338947fc88809a440ccd55cf6b4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 十一月 2023 16:39:52 +0800
Subject: [PATCH] funasr pages
---
funasr/bin/asr_infer.py | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/funasr/bin/asr_infer.py b/funasr/bin/asr_infer.py
index ef3ed6e..7015eb8 100644
--- a/funasr/bin/asr_infer.py
+++ b/funasr/bin/asr_infer.py
@@ -1605,7 +1605,6 @@
feats_lengths = to_device(feats_lengths, device=self.device)
enc_out, _, _ = self.asr_model.encoder(feats, feats_lengths)
-
nbest_hyps = self.beam_search(enc_out[0])
return nbest_hyps
@@ -1922,9 +1921,6 @@
):
from funasr.tasks.whisper import ASRTask
- from funasr.utils.whisper_utils.transcribe import transcribe
- from funasr.utils.whisper_utils.audio import pad_or_trim, log_mel_spectrogram
- from funasr.utils.whisper_utils.decoding import DecodingOptions, detect_language, decode
# 1. Build ASR model
scorers = {}
@@ -1987,6 +1983,10 @@
"""
+ from funasr.utils.whisper_utils.transcribe import transcribe
+ from funasr.utils.whisper_utils.audio import pad_or_trim, log_mel_spectrogram
+ from funasr.utils.whisper_utils.decoding import DecodingOptions, detect_language, decode
+
speech = speech[0]
speech = pad_or_trim(speech)
mel = log_mel_spectrogram(speech).to(self.device)
--
Gitblit v1.9.1