update readme, fix seaco bug

shixian.shi

2024-01-15 55c09aeaa25b4bb88a50e09ba68fa6ff00a6d676

 funasr/bin/inference.py

@@ -175,7 +175,7 @@
        # build tokenizer
        tokenizer = kwargs.get("tokenizer", None)
        if tokenizer is not None:
            tokenizer_class = tables.tokenizer_classes.get(tokenizer.lower())
            tokenizer_class = tables.tokenizer_classes.get(tokenizer)
            tokenizer = tokenizer_class(**kwargs["tokenizer_conf"])
            kwargs["tokenizer"] = tokenizer
            kwargs["token_list"] = tokenizer.token_list
@@ -186,13 +186,13 @@
        # build frontend
        frontend = kwargs.get("frontend", None)
        if frontend is not None:
            frontend_class = tables.frontend_classes.get(frontend.lower())
            frontend_class = tables.frontend_classes.get(frontend)
            frontend = frontend_class(**kwargs["frontend_conf"])
            kwargs["frontend"] = frontend
            kwargs["input_size"] = frontend.output_size()
        
        # build model
        model_class = tables.model_classes.get(kwargs["model"].lower())
        model_class = tables.model_classes.get(kwargs["model"])
        model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=vocab_size)
        model.eval()
        model.to(device)
@@ -245,7 +245,7 @@
        
            time1 = time.perf_counter()
            with torch.no_grad():
                results, meta_data = model.generate(**batch, **kwargs)
                results, meta_data = model.inference(**batch, **kwargs)
            time2 = time.perf_counter()
            
            asr_result_list.extend(results)
@@ -405,7 +405,7 @@
                spk_embedding = result['spk_embedding']
                labels = self.cb_model(spk_embedding, oracle_num=self.preset_spk_num)
                del result['spk_embedding']
                sv_output = postprocess(all_segments, None, labels, spk_embedding)
                sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
                if self.spk_mode == 'vad_segment':
                    sentence_list = []
                    for res, vadsegment in zip(restored_data, vadsegments):
@@ -443,7 +443,7 @@
        # build frontend
        frontend = kwargs.get("frontend", None)
        if frontend is not None:
            frontend_class = tables.frontend_classes.get(frontend.lower())
            frontend_class = tables.frontend_classes.get(frontend)
            frontend = frontend_class(**kwargs["frontend_conf"])

        self.frontend = frontend