| | |
|---|
| | | tokenizer = tokenizer_class(**kwargs["tokenizer_conf"]) |
|---|
| | | kwargs["tokenizer"] = tokenizer |
|---|
| | | kwargs["token_list"] = tokenizer.token_list |
|---|
| | | vocab_size = len(tokenizer.token_list) |
|---|
| | | else: |
|---|
| | | vocab_size = -1 |
|---|
| | | |
|---|
| | | # build frontend |
|---|
| | | frontend = kwargs.get("frontend", None) |
|---|
| | |
|---|
| | | |
|---|
| | | # build model |
|---|
| | | model_class = tables.model_classes.get(kwargs["model"].lower()) |
|---|
| | | model = model_class(**kwargs, **kwargs["model_conf"], |
|---|
| | | vocab_size=len(tokenizer.token_list) if tokenizer is not None else -1) |
|---|
| | | model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=vocab_size) |
|---|
| | | model.eval() |
|---|
| | | model.to(device) |
|---|
| | | |
|---|
| | |
|---|
| | | frontend = frontend_class(**kwargs["frontend_conf"]) |
|---|
| | | |
|---|
| | | self.frontend = frontend |
|---|
| | | if "frontend" in kwargs: |
|---|
| | | del kwargs["frontend"] |
|---|
| | | self.kwargs = kwargs |
|---|
| | | |
|---|
| | | |
|---|
| | | def __call__(self, input, input_len=None, kwargs=None, **cfg): |
|---|
| | | |
|---|
| | |
|---|
| | | time2 = time.perf_counter() |
|---|
| | | meta_data["load_data"] = f"{time2 - time1:0.3f}" |
|---|
| | | speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), |
|---|
| | | frontend=self.frontend) |
|---|
| | | frontend=self.frontend, **kwargs) |
|---|
| | | time3 = time.perf_counter() |
|---|
| | | meta_data["extract_feat"] = f"{time3 - time2:0.3f}" |
|---|
| | | meta_data["batch_data_time"] = speech_lengths.sum().item() * self.frontend.frame_shift * self.frontend.lfr_n / 1000 |
|---|
