| | |
|---|
| | | |
|---|
| | | Examples: |
|---|
| | | >>> import soundfile |
|---|
| | | >>> speech2text = Speech2Text("asr_config.yml", "asr.pth") |
|---|
| | | >>> speech2text = Speech2Text("asr_config.yml", "asr.pb") |
|---|
| | | >>> audio, rate = soundfile.read("speech.wav") |
|---|
| | | >>> speech2text(audio) |
|---|
| | | [(text, token, token_int, hypothesis object), ...] |
|---|
| | |
|---|
| | | # Input as audio signal |
|---|
| | | if isinstance(speech, np.ndarray): |
|---|
| | | speech = torch.tensor(speech) |
|---|
| | | |
|---|
| | | |
|---|
| | | if(speech.dim()==3): |
|---|
| | | speech = torch.squeeze(speech, 2) |
|---|
| | | #speech = speech.unsqueeze(0).to(getattr(torch, self.dtype)) |
|---|
| | | speech = speech.to(getattr(torch, self.dtype)) |
|---|
| | | # lenghts: (1,) |
|---|
