update readme, fix seaco bug

shixian.shi

2024-01-15 55c09aeaa25b4bb88a50e09ba68fa6ff00a6d676

 funasr/bin/inference.py

@@ -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)