atsr

语帆

2024-03-04 a2f263bd05498cf4f35d78ee0ee8755ba84d09ae

 examples/industrial_data_pretraining/lcbnet/demo.py

@@ -8,28 +8,6 @@
model = AutoModel(model="iic/LCB-NET",
                  model_revision="v1.0.0")

res = model.generate(input=("https://www.modelscope.cn/api/v1/models/iic/LCB-NET/repo?Revision=master&FilePath=example/asr_example.wav","https://www.modelscope.cn/api/v1/models/iic/LCB-NET/repo?Revision=master&FilePath=example/ocr.txt"),data_type=("sound", "text"))

# example1
res = model.generate(input='["~/.cache/modelscope/hub/iic/LCB-NET/example/asr_example.wav","~/.cache/modelscope/hub/iic/LCB-NET/example/ocr.txt"]',data_type='["sound", "text"]')

print(res)


'''
# tensor or numpy as input
# example2
import torchaudio
import os
wav_file = os.path.join(model.model_path, "example/asr_example.wav")
input_tensor, sample_rate = torchaudio.load(wav_file)
input_tensor = input_tensor.mean(0)
res = model.generate(input=[input_tensor], batch_size_s=300, is_final=True)


# example3
import soundfile

wav_file = os.path.join(model.model_path, "example/asr_example.wav")
speech, sample_rate = soundfile.read(wav_file)
res = model.generate(input=[speech], batch_size_s=300, is_final=True)
'''
print(res)