From 9b4e9cc8a0311e5243d69b73ed073e7ea441982e Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 27 三月 2024 16:05:29 +0800
Subject: [PATCH] train update
---
examples/industrial_data_pretraining/paraformer_streaming/demo.py | 38 ++++++++++++++++++--------------------
1 files changed, 18 insertions(+), 20 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 9923a04..57356b8 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -3,17 +3,17 @@
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
# MIT License (https://opensource.org/licenses/MIT)
+import os
+
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
+model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online")
-model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revison="v2.0.0")
-cache = {}
-res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
- cache=cache,
- is_final=True,
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+res = model.generate(input=wav_file,
chunk_size=chunk_size,
encoder_chunk_look_back=encoder_chunk_look_back,
decoder_chunk_look_back=decoder_chunk_look_back,
@@ -22,25 +22,23 @@
import soundfile
-import os
-speech, sample_rate = soundfile.read(os.path.expanduser('~')+
- "/.cache/modelscope/hub/damo/"+
- "speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/"+
- "example/asr_example.wav")
+
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+speech, sample_rate = soundfile.read(wav_file)
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