From f41a1276ff18cb9fd3d837dcda84a7650637d579 Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 14 九月 2023 12:25:44 +0800
Subject: [PATCH] add paraformer online opt infer code
---
funasr/bin/asr_inference_launch.py | 7 ++++---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index d5d1873..1b38f8f 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -953,14 +953,15 @@
# FIXME(kamo): The output format should be discussed about
raw_inputs = torch.unsqueeze(raw_inputs, axis=0)
asr_result_list = []
- cache = _prepare_cache(cache, chunk_size=chunk_size, batch_size=1)
+ cache = _prepare_cache(cache, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back,
+ decoder_chunk_look_back=decoder_chunk_look_back, batch_size=1)
item = {}
if data_path_and_name_and_type is not None and data_path_and_name_and_type[2] == "sound":
sample_offset = 0
speech_length = raw_inputs.shape[1]
stride_size = chunk_size[1] * 960
- cache = _prepare_cache(cache, chunk_size=chunk_size, batch_size=1,
- encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
+ cache = _prepare_cache(cache, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back,
+ decoder_chunk_look_back=decoder_chunk_look_back, batch_size=1)
final_result = ""
for sample_offset in range(0, speech_length, min(stride_size, speech_length - sample_offset)):
if sample_offset + stride_size >= speech_length - 1:
--
Gitblit v1.9.1