fastspeech2_aishell3效果很差

[William-HTP]

采用fastspeech2_aishell3和pwgan_aishell3合成音频，指定spk_id后仍然出现多个人声音，而且有些字读不清晰，请问是什么原因呢？ 代码如下： source path.sh FLAGS_allocator_strategy=naive_best_fit
FLAGS_fraction_of_gpu_memory_to_use=0.01
python3 ${BIN_DIR}/../synthesize_e2e.py
--am fastspeech2_aishell3
--am_config fastspeech2_aishell3_ckpt_1.1.0/default.yaml
--am_ckpt fastspeech2_aishell3_ckpt_1.1.0/snapshot_iter_96400.pdz
--am_stat fastspeech2_aishell3_ckpt_1.1.0/speech_stats.npy
--voc pwgan_aishell3
--voc_config pwg_aishell3_ckpt_0.5/default.yaml
--voc_ckpt pwg_aishell3_ckpt_0.5/snapshot_iter_1000000.pdz
--voc_stat pwg_aishell3_ckpt_0.5/feats_stats.npy
--lang zh
--text paddlespeech/t2s/assets/sentences.txt
--output_dir examples/aishell3/tts3/exp/default/test_e2e
--phones_dict fastspeech2_aishell3_ckpt_1.1.0/phone_id_map.txt
--speaker_dict fastspeech2_aishell3_ckpt_1.1.0/speaker_id_map.txt
--spk_id 0
--inference_dir examples/aishell3/tts3/exp/default/inference \