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