From a8591060d3889cd7a72841fa32a7ee64b49db1d2 Mon Sep 17 00:00:00 2001
From: msgk <zxr935867802@outlook.com>
Date: 星期五, 14 二月 2025 14:16:51 +0800
Subject: [PATCH] fix(spk): 修复 speaker embedding 集群后的重新排序问题
---
funasr/models/whisper/model.py | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/funasr/models/whisper/model.py b/funasr/models/whisper/model.py
index a332100..398eea3 100644
--- a/funasr/models/whisper/model.py
+++ b/funasr/models/whisper/model.py
@@ -9,6 +9,7 @@
from torch import nn
import whisper
+
# import whisper_timestamped as whisper
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
@@ -27,6 +28,7 @@
@tables.register("model_classes", "Whisper-large-v1")
@tables.register("model_classes", "Whisper-large-v2")
@tables.register("model_classes", "Whisper-large-v3")
+@tables.register("model_classes", "Whisper-large-v3-turbo")
@tables.register("model_classes", "WhisperWarp")
class WhisperWarp(nn.Module):
def __init__(self, *args, **kwargs):
@@ -111,10 +113,10 @@
# decode the audio
options = whisper.DecodingOptions(**kwargs.get("DecodingOptions", {}))
-
- result = whisper.decode(self.model, speech, language='english')
+
+ result = whisper.decode(self.model, speech, options=options)
# result = whisper.transcribe(self.model, speech)
-
+
results = []
result_i = {"key": key[0], "text": result.text}
--
Gitblit v1.9.1