From e8f80e96f99cb856423d030c7d055c302a6d3278 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 17 四月 2024 21:23:20 +0800
Subject: [PATCH] Dev gzf exp (#1627)
---
funasr/models/whisper/model.py | 10 ++++++----
1 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/funasr/models/whisper/model.py b/funasr/models/whisper/model.py
index 73d70d7..51fde81 100644
--- a/funasr/models/whisper/model.py
+++ b/funasr/models/whisper/model.py
@@ -41,6 +41,8 @@
self.model = model
+ self.encoder_output_size = self.model.dims.n_audio_state
+
def forward(self, ):
pass
@@ -88,12 +90,12 @@
speech = speech.to(device=kwargs["device"])[0, :, :]
speech_lengths = speech_lengths.to(device=kwargs["device"])
- # detect the spoken language
- _, probs = self.model.detect_language(speech)
- print(f"Detected language: {max(probs, key=probs.get)}")
+ # # detect the spoken language
+ # _, probs = self.model.detect_language(speech)
+ # print(f"Detected language: {max(probs, key=probs.get)}")
# decode the audio
- options = whisper.DecodingOptions(language=kwargs.get("language", None), fp16=False)
+ options = whisper.DecodingOptions(**kwargs.get("DecodingOptions", {}))
result = whisper.decode(self.model, speech, options)
results = []
--
Gitblit v1.9.1