{
  "name": "FastSpeech2",
  "id": "ie2sc9g1qk00",
  "description": "FastSpeech2 是一种高效的端到端语音合成模型。相比 FastSpeech，FastSpeech2 引入了多尺度时长预测器和能量 / 基频预测分支，优化了时长预测模块并新增韵律特征建模，在合成速度和语音自然度上均有大幅提升。",
  "category": "音频",
  "framework": [
    "PyTorch"
  ],
  "supportOs": [
    "OpenHarmony",
    "Linux"
  ],
  "computingPower": [
    "Hi3403V100 SVP_NNN"
  ],
  "tags": [
    "文本转语音"
  ],
  "repositoryUrl": "https://gitee.com/HiSpark/modelzoo/blob/master/samples/built-in/audio/FastSpeech2/README.md",
  "licenseUrl": "https://github.com/ming024/FastSpeech2/blob/master/LICENSE",
  "downloads": [
    {
      "fileName": "fastspeech_hifigan_en.onnx",
      "variants": [
        "源模型 / 源模型下载",
        "源模型 / 源模型元数据",
        "编译模型 / OM 元数据 / a16w8"
      ]
    }
  ],
  "apiDetail": {
    "createdBy": 139318985286440,
    "creationDate": "2026-01-08 16:18:57",
    "creationUserCN": "sloanqin",
    "lastUpdatedBy": null,
    "lastUpdateDate": "2026-01-09 15:08:50",
    "lastUpdateUserCN": "sloanqin",
    "rowIdx": -1,
    "id": "ie2sc9g1qk00",
    "name": "FastSpeech2",
    "isBeta": 1,
    "betaVersionDesc": "CANN包版本需要适配修改待发布",
    "description": "FastSpeech2 是一种高效的端到端语音合成模型。相比 FastSpeech，FastSpeech2 引入了多尺度时长预测器和能量 / 基频预测分支，优化了时长预测模块并新增韵律特征建模，在合成速度和语音自然度上均有大幅提升。",
    "parentId": "ie2sc9g1qk00",
    "coverImageId": 1722265270026243,
    "coverImageUrl": "https://openxinhuo-board-image.obs.cn-east-3.myhuaweicloud.com/1722265270026243%2Ffastspeech2.jpg",
    "modelEffectId": null,
    "modelEffectUrl": "",
    "computerVersion": [],
    "naturalLanguageProcess": [],
    "multimodal": [],
    "video": [
      "文本转语音"
    ],
    "framework": [
      "PyTorch"
    ],
    "modelRepository": "https://gitee.com/HiSpark/modelzoo/blob/master/samples/built-in/audio/FastSpeech2/README.md",
    "originModel": [
      {
        "id": "1722129101946883",
        "name": "fastspeech_hifigan_en.onnx",
        "url": null,
        "size": "142724651"
      }
    ],
    "originModelLink": null,
    "dataSet": "https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2",
    "modelLicense": "https://github.com/ming024/FastSpeech2/blob/master/LICENSE",
    "detailParams": [
      {
        "name": "输入",
        "value": "1x40"
      },
      {
        "name": "参数量",
        "value": "35.266M"
      },
      {
        "name": "计算量",
        "value": "29.162GFLOPs"
      }
    ],
    "quickStart": {
      "url": "https://gitee.com/HiSpark/modelzoo/blob/master/samples/built-in/audio/FastSpeech2",
      "markDownUrl": "",
      "developLanguage": [
        {
          "language": "C++",
          "context": "{\"ops\":[{\"attributes\":{\"line-height\":\"1.6\",\"color\":\"#40485b\",\"size\":\"16px\",\"background\":\"#ffffff\"},\"insert\":\"模型可以通过以下代码完成快速推理\"},{\"attributes\":{\"text-indent\":\"0px\"},\"insert\":\"\\n\"},{\"insert\":\"#include \\\"model.h\\\"\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"#include \\\"log.h\\\"\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\\n\"},{\"insert\":\"using namespace Infer;\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\\n\"},{\"insert\":\"int main()\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"{\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    EnvInit();\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    std::string omModelPath = \\\"/path/to/model.om\\\"; // 模型文件路径 \"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    std::string filePath= \\\"/path/to/file_list.json\\\"; // 输入文本文件路径\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    std::unique_ptr<Model> model = std::make_unique<Model>();\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    if (model->Load(omModelPath, ModelType::FastSpeech2) != 0) {\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"        LOG(ERROR) << \\\"fail to load model\\\";\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"        return -1;\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    }\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    auto ret = model->Infer(filePath, FileType::JsonFile);\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    if (ret.size() == 0) {\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"        LOG(ERROR) << \\\"fail to infer model\\\";\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"        model->Unload();\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"        return -1;\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    }\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    if (model->Unload() != 0) {\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"        LOG(ERROR) << \\\"fail to unload model\\\";\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"        return -1;\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    }\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    EnvDeinit();\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"    return 0;\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"insert\":\"}\"},{\"attributes\":{\"code-block\":\"plain\"},\"insert\":\"\\n\"},{\"attributes\":{\"line-height\":\"1.6\",\"color\":\"#40485b\",\"size\":\"16px\",\"background\":\"#ffffff\"},\"insert\":\"备注：上述C++代码依赖的动态库与头文件位于\"},{\"attributes\":{\"line-height\":\"1.6\",\"color\":\"#095eab\",\"size\":\"16px\",\"background\":\"transparent\",\"link\":\"https://gitee.com/HiSpark/modelzoo/tree/master/samples/common\"},\"insert\":\"/samples/common\"},{\"attributes\":{\"line-height\":\"1.6\",\"color\":\"#40485b\",\"size\":\"16px\",\"background\":\"#ffffff\"},\"insert\":\"目录下，编译相关配置参考\"},{\"attributes\":{\"line-height\":\"1.6\",\"color\":\"#095eab\",\"size\":\"16px\",\"background\":\"transparent\",\"link\":\"https://gitee.com/HiSpark/modelzoo/blob/master/samples/built-in/audio/FastSpeech2/src/CMakeLists.txt\"},\"insert\":\"CMakeLists.txt\"},{\"attributes\":{\"line-height\":\"1.6\",\"color\":\"#40485b\",\"size\":\"16px\",\"background\":\"#ffffff\"},\"insert\":\"。\"},{\"attributes\":{\"text-indent\":\"0px\"},\"insert\":\"\\n\"},{\"insert\":\"\\n\"}]}"
        }
      ]
    },
    "status": "released",
    "currentHandler": "",
    "currentHandlerName": "",
    "jsonPath": "https://gitee.com/sloanqin/modelzoo-dev/blob/fastspeech2/samples/built-in/audio/FastSpeech2/fastspeech2.json",
    "modelAdaptor": [
      {
        "createdBy": null,
        "creationDate": null,
        "creationUserCN": null,
        "lastUpdatedBy": null,
        "lastUpdateDate": null,
        "lastUpdateUserCN": null,
        "rowIdx": -1,
        "id": "i8ttm5k1tc00",
        "name": "Hi3403V100 SVP_NNN",
        "modelId": "ie2sc9g1qk00",
        "modelName": "FastSpeech2",
        "supportNames": [
          "a16w8"
        ],
        "toolkit": [
          {
            "name": "CANN配置",
            "url": "",
            "desc": "6.10.t01spc030b660；(请联系FAE获取)",
            "imgId": "cann"
          },
          {
            "name": "编译工具库",
            "url": "https://gitee.com/HiSpark/pegasus/blob/Beta-v0.9.1/docs/Hi3403V100%E7%8E%AF%E5%A2%83%E6%90%AD%E5%BB%BA%E6%8C%87%E5%8D%97/Hi3403V100%E7%8E%AF%E5%A2%83%E6%90%AD%E5%BB%BA%E6%8C%87%E5%8D%97.md",
            "desc": "高效编译，精准适配；AI性能优化，应用流畅运行",
            "imgId": "tool"
          },
          {
            "name": "SDK",
            "url": "https://gitee.com/HiSpark/ss928v100_clang/tree/Beta-v0.9.1/",
            "desc": "稳定、易用的设计；支撑客户快速产品量产",
            "imgId": "sdk"
          }
        ],
        "supportOs": [
          "OpenHarmony",
          "Linux"
        ],
        "supportQuantify": [
          {
            "createdBy": 132241120926760,
            "creationDate": "2026-03-26 19:50:46",
            "creationUserCN": "liaoshibin",
            "lastUpdatedBy": 132241120926760,
            "lastUpdateDate": "2026-03-26 19:50:46",
            "lastUpdateUserCN": "liaoshibin",
            "rowIdx": -1,
            "id": "j6tf932ci000",
            "name": "a16w8",
            "computingId": "i8ttm5k1tc00",
            "computingName": "Hi3403V100 SVP_NNN",
            "omOfflineModelUrl": null,
            "omOfflineModelId": 1722129460559875,
            "omOfflineModelSize": "40041177",
            "omOfflineModelName": "fastspeech_hifigan_en.om",
            "omOfflineModel": [
              {
                "id": "1722129460559875",
                "name": "fastspeech_hifigan_en.om",
                "url": null,
                "size": "40041177"
              }
            ],
            "omOfflineModelLink": null,
            "releaseTime": "2026-01-11",
            "boardOs": null,
            "modelLicense": "https://gitee.com/HiSpark/modelzoo/blob/master/samples/built-in/audio/FastSpeech2/LICENSE",
            "modelPerformance": [
              {
                "performanceValue": "52.49",
                "unit": "耗时（ms）",
                "desc": null
              },
              {
                "performanceValue": "19.05",
                "unit": "性能（fps）",
                "desc": ""
              },
              {
                "performanceValue": "488.799",
                "unit": "单帧内存带宽（MB）",
                "desc": ""
              },
              {
                "performanceValue": "1.418",
                "unit": "内存（MB）",
                "desc": ""
              }
            ],
            "deleted": 0
          }
        ],
        "deleted": 0
      }
    ],
    "saveType": null,
    "deleteType": null,
    "latest": "Y",
    "deleted": 0,
    "modelPhase": "released",
    "remark": null,
    "fileInfo": null,
    "reviewType": null,
    "owner": "sloanqin",
    "ownerBy": 139318985286440,
    "optional": null,
    "optionalList": [
      "whalenowings",
      "0e900d99dee8461b8"
    ],
    "optionalBy": null,
    "downloadNum": 23,
    "collectNum": null,
    "isCollect": null
  }
}