trainer

游雁

2024-03-21 24aea85b5bc3f354d683201fa9e37968f3f1638f

 examples/industrial_data_pretraining/paraformer_streaming/demo.py

@@ -3,13 +3,16 @@
# 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 = [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
wav_file="/Users/zhifu/Downloads/NCYzUhAtZNI_0015.wav"
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_revision="v2.0.4")

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,
@@ -17,12 +20,11 @@
            )
print(res)

# exit()

import soundfile
import os

# wav_file = os.path.join(model.model_path, "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、480ms