update paraformer online README

haoneng.lhn

2023-09-25 c45b89970645ae4c05bd29114b0c1b1e31f70cbc

 egs_modelscope/asr/TEMPLATE/README_zh.md

@@ -27,15 +27,18 @@
inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
    model_revision='v1.0.6',
    model_revision='v1.0.7',
    update_model=False,
    mode='paraformer_streaming'
    )
import soundfile
speech, sample_rate = soundfile.read("example/asr_example.wav")

chunk_size = [5, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size}
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
param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size,
              "encoder_chunk_look_back": encoder_chunk_look_back, "decoder_chunk_look_back": decoder_chunk_look_back}
chunk_stride = chunk_size[1] * 960 # 600ms、480ms
# first chunk, 600ms
speech_chunk = speech[0:chunk_stride]
@@ -55,7 +58,7 @@
inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online',
    model_revision='v1.0.6',
    model_revision='v1.0.7',
    update_model=False,
    mode="paraformer_fake_streaming"
)