Funasr1.0 (#1279)

zhifu gao

2024-01-22 3919d7454c070702e94b149e4032e9db08d28fa3

 README_zh.md

@@ -87,12 +87,13 @@
from funasr import AutoModel
# 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, 
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="v2.0.3",
                  # spk_model="cam++", spk_model_revision="v2.0.2",
                  )
res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
            batch_size_s=300, 
            hotword='魔搭')
print(res)
```
@@ -121,7 +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.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)
```

@@ -134,7 +135,7 @@
model = AutoModel(model="fsmn-vad", model_revision="v2.0.2")

wav_file = f"{model.model_path}/example/asr_example.wav"
res = model(input=wav_file)
res = model.generate(input=wav_file)
print(res)
```

@@ -156,7 +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.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
    if len(res[0]["value"]):
        print(res)
```
@@ -167,7 +168,7 @@

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")
res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
print(res)
```

@@ -179,10 +180,10 @@

wav_file = f"{model.model_path}/example/asr_example.wav"
text_file = f"{model.model_path}/example/text.txt"
res = model(input=(wav_file, text_file), data_type=("sound", "text"))
res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
print(res)
```
更多详细用法（[示例](examples/industrial_data_pretraining)）
更多详细用法（[示例](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)）


<a name="服务部署"></a>
@@ -242,4 +243,10 @@
  pages={2063--2067},
  doi={10.21437/Interspeech.2022-9996}
}
@article{shi2023seaco,
  author={Xian Shi and Yexin Yang and Zerui Li and Yanni Chen and Zhifu Gao and Shiliang Zhang},
  title={{SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability}},
  year=2023,
  journal={arXiv preprint arXiv:2308.03266(accepted by ICASSP2024)},
}
```