From 1596f6f414f6f41da66506debb1dff19fffeb3ec Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 24 六月 2024 11:55:17 +0800
Subject: [PATCH] fixbug hotwords
---
examples/industrial_data_pretraining/scama/demo.py | 42 +++++++++++++++++++++++-------------------
1 files changed, 23 insertions(+), 19 deletions(-)
diff --git a/examples/industrial_data_pretraining/scama/demo.py b/examples/industrial_data_pretraining/scama/demo.py
index 9d458ab..00d85ae 100644
--- a/examples/industrial_data_pretraining/scama/demo.py
+++ b/examples/industrial_data_pretraining/scama/demo.py
@@ -5,17 +5,20 @@
from funasr import AutoModel
-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
+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="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming")
+model = AutoModel(
+ model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming"
+)
cache = {}
-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,
- )
+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,
+)
print(res)
@@ -25,18 +28,19 @@
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
+chunk_stride = chunk_size[1] * 960 # 600ms銆�480ms
cache = {}
-total_chunk_num = 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]
+ speech_chunk = speech[i * chunk_stride : (i + 1) * chunk_stride]
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,
- )
+ 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