LiXin
LiXin
### 初步测试 在推理过程,基于gpt2实现llama2结果与原始llama相同,均为 ``` [{'generated_text': 'Give three tips for staying healthy.\nWhat is the best way to stay healthy?\nWhat are the 5 ways to stay healthy?\nWhat are the 5 ways to...
作者您好,在eval/elo/0elo.py代码提到了两个文件夹: ```python elo_data_path = "eval/elo/elo_data/" elo_outputs_path = "eval/elo/gpt4_elo_outputs/" ``` 可以提供这两个目录下面的jsonl文件吗?要不然评测部分代码(eval/elo/0elo.py)没办法运行。
目前解决方案 ```python def worker_process(): wav_files = glob.glob('data/*/*/*.wav') for wav_file in wav_files: print('processing ',wav_file) output_path =f'{wav_file[:-4]}.json' start_time = time.time() model= AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", spk_model="cam++") ans = model.generate(input=wav_file,batch_size_s=300,hotword='', ) os.system(f'rm "{wav_file}"') end_time...
> 目前只能不断初始化么,有没有办法可以维持这个实例啊 后来没研究了 我也很期待修复这个bug