| | |
|---|
| | | super().__init__() |
|---|
| | | |
|---|
| | | if specaug is not None: |
|---|
| | | specaug_class = tables.specaug_classes.get(specaug.lower()) |
|---|
| | | specaug_class = tables.specaug_classes.get(specaug) |
|---|
| | | specaug = specaug_class(**specaug_conf) |
|---|
| | | if normalize is not None: |
|---|
| | | normalize_class = tables.normalize_classes.get(normalize.lower()) |
|---|
| | | normalize_class = tables.normalize_classes.get(normalize) |
|---|
| | | normalize = normalize_class(**normalize_conf) |
|---|
| | | encoder_class = tables.encoder_classes.get(encoder.lower()) |
|---|
| | | encoder_class = tables.encoder_classes.get(encoder) |
|---|
| | | encoder = encoder_class(input_size=input_size, **encoder_conf) |
|---|
| | | encoder_output_size = encoder.output_size() |
|---|
| | | predictor_class = tables.predictor_classes.get(predictor.lower()) |
|---|
| | | predictor_class = tables.predictor_classes.get(predictor) |
|---|
| | | predictor = predictor_class(**predictor_conf) |
|---|
| | | self.specaug = specaug |
|---|
| | | self.normalize = normalize |
|---|
| | |
|---|
| | | meta_data["extract_feat"] = f"{time3 - time2:0.3f}" |
|---|
| | | meta_data["batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000 |
|---|
| | | |
|---|
| | | speech.to(device=kwargs["device"]), speech_lengths.to(device=kwargs["device"]) |
|---|
| | | speech = speech.to(device=kwargs["device"]) |
|---|
| | | speech_lengths = speech_lengths.to(device=kwargs["device"]) |
|---|
| | | |
|---|
| | | # Encoder |
|---|
| | | encoder_out, encoder_out_lens = self.encode(speech, speech_lengths) |
|---|
