| | |
|---|
| | | from funasr.utils.timestamp_tools import timestamp_sentence |
|---|
| | | from funasr.download.download_from_hub import download_model |
|---|
| | | from funasr.utils.vad_utils import slice_padding_audio_samples |
|---|
| | | from funasr.utils.vad_utils import merge_vad |
|---|
| | | from funasr.utils.load_utils import load_audio_text_image_video |
|---|
| | | from funasr.train_utils.set_all_random_seed import set_all_random_seed |
|---|
| | | from funasr.train_utils.load_pretrained_model import load_pretrained_model |
|---|
| | |
|---|
| | | kwargs["token_list"] = tokenizer.token_list if hasattr(tokenizer, "token_list") else None |
|---|
| | | kwargs["token_list"] = tokenizer.get_vocab() if hasattr(tokenizer, "get_vocab") else kwargs["token_list"] |
|---|
| | | vocab_size = len(kwargs["token_list"]) if kwargs["token_list"] is not None else -1 |
|---|
| | | if vocab_size == -1 and hasattr(tokenizer, "get_vocab_size"): |
|---|
| | | vocab_size = tokenizer.get_vocab_size() |
|---|
| | | else: |
|---|
| | | vocab_size = -1 |
|---|
| | | kwargs["tokenizer"] = tokenizer |
|---|
| | |
|---|
| | | load_pretrained_model( |
|---|
| | | model=model, |
|---|
| | | path=init_param, |
|---|
| | | ignore_init_mismatch=kwargs.get("ignore_init_mismatch", False), |
|---|
| | | ignore_init_mismatch=kwargs.get("ignore_init_mismatch", True), |
|---|
| | | oss_bucket=kwargs.get("oss_bucket", None), |
|---|
| | | scope_map=kwargs.get("scope_map", []), |
|---|
| | | excludes=kwargs.get("excludes", None), |
|---|
| | |
|---|
| | | else: |
|---|
| | | print(f"error, init_param does not exist!: {init_param}") |
|---|
| | | |
|---|
| | | # fp16 |
|---|
| | | if kwargs.get("fp16", False): |
|---|
| | | model.to(torch.float16) |
|---|
| | | return model, kwargs |
|---|
| | | |
|---|
| | | def __call__(self, *args, **cfg): |
|---|
| | |
|---|
| | | res = self.inference(input, input_len=input_len, model=self.vad_model, kwargs=self.vad_kwargs, **cfg) |
|---|
| | | end_vad = time.time() |
|---|
| | | |
|---|
| | | # FIX(gcf): concat the vad clips for sense vocie model for better aed |
|---|
| | | if kwargs.get("merge_vad", False): |
|---|
| | | for i in range(len(res)): |
|---|
| | | res[i]['value'] = merge_vad(res[i]['value'], kwargs.get("merge_length", 15000)) |
|---|
| | | |
|---|
| | | # step.2 compute asr model |
|---|
| | | model = self.model |
|---|
| | |
|---|
| | | return_raw_text = kwargs.get('return_raw_text', False) |
|---|
| | | # step.3 compute punc model |
|---|
| | | if self.punc_model is not None: |
|---|
| | | if not len(result["text"]): |
|---|
| | | if not len(result["text"].strip()): |
|---|
| | | if return_raw_text: |
|---|
| | | result['raw_text'] = '' |
|---|
| | | else: |
|---|
