| | |
|---|
| | | # spk_model_revision="v2.0.2", |
|---|
| | | ) |
|---|
| | | |
|---|
| | | |
|---|
| | | # example1 |
|---|
| | | res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", |
|---|
| | | hotword='达摩院 魔搭', |
|---|
| | | # sentence_timestamp=True, # return sentence level information when spk_model is not given |
|---|
| | | ) |
|---|
| | | print(res) |
|---|
| | | print(res) |
|---|
| | | |
|---|
| | | # example2 |
|---|
| | | import torchaudio |
|---|
| | | 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 |
|---|
| | | import os |
|---|
| | | 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) |
|---|
| | | |
|---|
