From 3919d7454c070702e94b149e4032e9db08d28fa3 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 22 一月 2024 15:42:45 +0800
Subject: [PATCH] Funasr1.0 (#1279)
---
examples/industrial_data_pretraining/paraformer_streaming/demo.py | 17 ++++++++---------
1 files changed, 8 insertions(+), 9 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 8f7eef3..6898030 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -10,8 +10,7 @@
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.2")
-cache = {}
-res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
chunk_size=chunk_size,
encoder_chunk_look_back=encoder_chunk_look_back,
decoder_chunk_look_back=decoder_chunk_look_back,
@@ -32,11 +31,11 @@
for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
is_final = i == total_chunk_num - 1
- res = model(input=speech_chunk,
- cache=cache,
- is_final=is_final,
- chunk_size=chunk_size,
- encoder_chunk_look_back=encoder_chunk_look_back,
- decoder_chunk_look_back=decoder_chunk_look_back,
- )
+ res = model.generate(input=speech_chunk,
+ cache=cache,
+ is_final=is_final,
+ chunk_size=chunk_size,
+ encoder_chunk_look_back=encoder_chunk_look_back,
+ decoder_chunk_look_back=decoder_chunk_look_back,
+ )
print(res)
--
Gitblit v1.9.1