| | |
|---|
| | | chars = string.ascii_letters + string.digits |
|---|
| | | if isinstance(data_in, str) and data_in.startswith('http'): # url |
|---|
| | | data_in = download_from_url(data_in) |
|---|
| | | |
|---|
| | | if isinstance(data_in, str) and os.path.exists(data_in): # wav_path; filelist: wav.scp, file.jsonl;text.txt; |
|---|
| | | _, file_extension = os.path.splitext(data_in) |
|---|
| | | file_extension = file_extension.lower() |
|---|
| | |
|---|
| | | kwargs = download_model(**kwargs) |
|---|
| | | |
|---|
| | | set_all_random_seed(kwargs.get("seed", 0)) |
|---|
| | | |
|---|
| | | |
|---|
| | | device = kwargs.get("device", "cuda") |
|---|
| | | if not torch.cuda.is_available() or kwargs.get("ngpu", 1) == 0: |
|---|
| | | device = "cpu" |
|---|
| | |
|---|
| | | vocab_size = len(tokenizer.token_list) |
|---|
| | | else: |
|---|
| | | vocab_size = -1 |
|---|
| | | pdb.set_trace() |
|---|
| | | # build frontend |
|---|
| | | frontend = kwargs.get("frontend", None) |
|---|
| | | |
|---|
| | | if frontend is not None: |
|---|
| | | frontend_class = tables.frontend_classes.get(frontend) |
|---|
| | | frontend = frontend_class(**kwargs["frontend_conf"]) |
|---|
| | | kwargs["frontend"] = frontend |
|---|
| | | kwargs["input_size"] = frontend.output_size() |
|---|
| | | pdb.set_trace() |
|---|
| | | |
|---|
| | | # build model |
|---|
| | | model_class = tables.model_classes.get(kwargs["model"]) |
|---|
| | | model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=vocab_size) |
|---|
| | | |
|---|
| | | model.to(device) |
|---|
| | | |
|---|
| | | # init_param |
|---|
| | |
|---|
| | | batch_size = kwargs.get("batch_size", 1) |
|---|
| | | # if kwargs.get("device", "cpu") == "cpu": |
|---|
| | | # batch_size = 1 |
|---|
| | | |
|---|
| | | |
|---|
| | | key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=kwargs.get("data_type", None), key=key) |
|---|
| | | |
|---|
| | | speed_stats = {} |
|---|
| | |
|---|
| | | |
|---|
| | | time1 = time.perf_counter() |
|---|
| | | with torch.no_grad(): |
|---|
| | | pdb.set_trace() |
|---|
| | | results, meta_data = model.inference(**batch, **kwargs) |
|---|
| | | time2 = time.perf_counter() |
|---|
| | | |
|---|
| | | pdb.set_trace() |
|---|
| | | asr_result_list.extend(results) |
|---|
| | | |
|---|
| | | # batch_data_time = time_per_frame_s * data_batch_i["speech_lengths"].sum().item() |
|---|
