From dde41de2955d4aae52a2badb63f903a8fab7208d Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 29 七月 2024 11:39:33 +0800
Subject: [PATCH] dcos
---
funasr/models/whisper/model.py | 9 +++++++--
1 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/funasr/models/whisper/model.py b/funasr/models/whisper/model.py
index 8e9245a..a332100 100644
--- a/funasr/models/whisper/model.py
+++ b/funasr/models/whisper/model.py
@@ -7,7 +7,10 @@
import torch.nn.functional as F
from torch import Tensor
from torch import nn
+
import whisper
+# import whisper_timestamped as whisper
+
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.register import tables
@@ -108,8 +111,10 @@
# decode the audio
options = whisper.DecodingOptions(**kwargs.get("DecodingOptions", {}))
- result = whisper.decode(self.model, speech, options)
-
+
+ result = whisper.decode(self.model, speech, language='english')
+ # result = whisper.transcribe(self.model, speech)
+
results = []
result_i = {"key": key[0], "text": result.text}
--
Gitblit v1.9.1