update readme

shixian.shi

2024-01-15 19645da9e998581e6329d679bae968d0c45d1895

 README_zh.md

@@ -86,12 +86,15 @@
### 非实时语音识别
```python
from funasr import AutoModel

model = AutoModel(model="paraformer-zh")
# for the long duration wav, you could add vad model
# model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc")

res = model(input="asr_example_zh.wav", batch_size=64)
# paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh", model_revision="v2.0.2", \
                  vad_model="fsmn-vad", vad_model_revision="v2.0.2", \
                  punc_model="ct-punc-c", punc_model_revision="v2.0.2", \
                  spk_model="cam++", spk_model_revision="v2.0.2")
res = model(input=f"{model.model_path}/example/asr_example.wav", 
            batch_size=64, 
            hotword='魔搭')
print(res)
```
注：`model_hub`：表示模型仓库，`ms`为选择modelscope下载，`hf`为选择huggingface下载。
@@ -105,7 +108,7 @@
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="paraformer-zh-streaming", model_revision="v2.0.0")
model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.2")

import soundfile
import os
@@ -119,13 +122,7 @@
for i in range(total_chunk_num):
    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
    is_final = i == total_chunk_num - 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,
                )
    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)
    print(res)
```

@@ -160,11 +157,7 @@
for i in range(total_chunk_num):
    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
    is_final = i == total_chunk_num - 1
    res = model(input=speech_chunk,
                cache=cache,
                is_final=is_final,
                chunk_size=chunk_size,
                )
    res = model(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
    if len(res[0]["value"]):
        print(res)
```
@@ -173,7 +166,7 @@
```python
from funasr import AutoModel

model = AutoModel(model="ct-punc", model_revision="v2.0.1")
model = AutoModel(model="ct-punc", model_revision="v2.0.2")

res = model(input="那今天的会就到这里吧 happy new year 明年见")
print(res)
@@ -186,9 +179,8 @@
model = AutoModel(model="fa-zh", model_revision="v2.0.0")

wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/asr_example.wav"
res = model(input=(wav_file, text_file),
            data_type=("sound", "text"))
text_file = f"{model.model_path}/example/text.txt"
res = model(input=(wav_file, text_file), data_type=("sound", "text"))
print(res)
```
更多详细用法（[示例](examples/industrial_data_pretraining)）