| | |
|---|
| | | from funasr.models.campplus.cluster_backend import ClusterBackend |
|---|
| | | except: |
|---|
| | | print("If you want to use the speaker diarization, please `pip install hdbscan`") |
|---|
| | | import pdb |
|---|
| | | |
|---|
| | | |
|---|
| | | def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None): |
|---|
| | | """ |
|---|
| | |
|---|
| | | 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() |
|---|
| | |
|---|
| | | vocab_size = len(kwargs["token_list"]) if kwargs["token_list"] is not None else -1 |
|---|
| | | else: |
|---|
| | | vocab_size = -1 |
|---|
| | | |
|---|
| | | # build frontend |
|---|
| | | frontend = kwargs.get("frontend", None) |
|---|
| | | kwargs["input_size"] = None |
|---|
| | |
|---|
| | | # 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 |
|---|
| | |
|---|
| | | data_batch = data_list[beg_idx:end_idx] |
|---|
| | | key_batch = key_list[beg_idx:end_idx] |
|---|
| | | batch = {"data_in": data_batch, "key": key_batch} |
|---|
| | | |
|---|
| | | if (end_idx - beg_idx) == 1 and kwargs.get("data_type", None) == "fbank": # fbank |
|---|
| | | batch["data_in"] = data_batch[0] |
|---|
| | | batch["data_lengths"] = input_len |
|---|
