From 0143122a4e2ee86cc27ba137b2bb0530577cbf12 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 12 一月 2024 10:27:36 +0800
Subject: [PATCH] funasr1.0 streaming demo
---
examples/industrial_data_pretraining/paraformer_streaming/demo.py | 10 +++-------
1 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 9923a04..d4dd34e 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -9,11 +9,9 @@
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="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revison="v2.0.0")
+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",
- cache=cache,
- is_final=True,
chunk_size=chunk_size,
encoder_chunk_look_back=encoder_chunk_look_back,
decoder_chunk_look_back=decoder_chunk_look_back,
@@ -24,10 +22,8 @@
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
--
Gitblit v1.9.1