From e9d2cfc3a134b00f4e98271fbee3838d1ccecbcc Mon Sep 17 00:00:00 2001
From: VirtuosoQ <2416050435@qq.com>
Date: 星期五, 26 四月 2024 14:59:30 +0800
Subject: [PATCH] FunASR java http client
---
funasr/models/lcbnet/model.py | 11 +++++++----
1 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/funasr/models/lcbnet/model.py b/funasr/models/lcbnet/model.py
index deddf73..3ac319c 100644
--- a/funasr/models/lcbnet/model.py
+++ b/funasr/models/lcbnet/model.py
@@ -427,7 +427,10 @@
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
audio_sample_list = sample_list[0]
- ocr_sample_list = sample_list[1]
+ if len(sample_list) >1:
+ ocr_sample_list = sample_list[1]
+ else:
+ ocr_sample_list = [[294, 0]]
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
frontend=frontend)
time3 = time.perf_counter()
@@ -441,10 +444,10 @@
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
if isinstance(encoder_out, tuple):
encoder_out = encoder_out[0]
-
+
ocr_list_new = [[x + 1 if x != 0 else x for x in sublist] for sublist in ocr_sample_list]
- ocr = torch.tensor(ocr_list_new)
- ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1))
+ ocr = torch.tensor(ocr_list_new).to(device=kwargs["device"])
+ ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1)).to(device=kwargs["device"])
ocr, ocr_lens, _ = self.text_encoder(ocr, ocr_lengths)
fusion_out, _, _, _ = self.fusion_encoder(encoder_out,None, ocr, None)
encoder_out = encoder_out + fusion_out
--
Gitblit v1.9.1