From 94de39dde2e616a01683c518023d0fab72b4e103 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 19 二月 2024 22:21:50 +0800
Subject: [PATCH] aishell example
---
examples/industrial_data_pretraining/paraformer_streaming/demo.py | 31 +++++++++++++++----------------
1 files changed, 15 insertions(+), 16 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index d4dd34e..455fe84 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -5,13 +5,12 @@
from funasr import AutoModel
-chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
-encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
-decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
+chunk_size = [5, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
+encoder_chunk_look_back = 0 #number of chunks to lookback for encoder self-attention
+decoder_chunk_look_back = 0 #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="v2.0.0")
-cache = {}
-res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+model = AutoModel(model="damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.4")
+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,
@@ -28,15 +27,15 @@
chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
cache = {}
-
-for i in range(int(len((speech)-1)/chunk_stride+1)):
+total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
- is_final = i == int(len((speech)-1)/chunk_stride+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,
- )
+ is_final = i == total_chunk_num - 1
+ 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