This repository is published as an Ascend NPU model repository. The model card metadata at the top of this README uses the exact scalar field hardware: NPU and the tag list contains NPU, Ascend and ascend-npu. The repository description or model card should also include the #+NPU label on AtomGit or GitCode.
| Item | Value |
|---|---|
| Repository | https://gitcode.com/nanyizjm/Kokoro-82M-Ascend-NPU |
| Competition task | Track 1 model adaptation |
| Hardware metadata | hardware: NPU |
| Required tag | #+NPU |
| README data policy | Inference, accuracy and performance values are written as text in this README; images are not used as a replacement for data. |
| Item | Value |
|---|---|
| Model repository | https://gitcode.com/nanyizjm/Kokoro-82M-Ascend-NPU |
| Original model or weight source | https://gitcode.com/hf_mirrors/AI-ModelScope/Kokoro-82M |
| Competition track | Track 1: model adaptation |
| Target hardware | Ascend NPU |
| Required function | NPU inference runs successfully or the blocking reason is explicitly recorded |
| Required accuracy | NPU result compared with CPU/GPU reference, error less than 1 percent |
| Required tag | #+NPU |
| Deliverable | Status |
|---|---|
| inference.py | Present |
| readme.md / README.md | Present |
| eval/eval_accuracy.py | Present |
| eval/eval_performance.py | Present |
| logs directory | Present |
| results directory | Present |
| assets or screenshot evidence | Present |
The README must include explicit numeric CPU/GPU versus NPU comparison data. The key acceptance target is error less than 1 percent. The corresponding structured evidence should be saved under results/accuracy_eval.json and logs/accuracy_eval.log when available.
#+NPU
This section is written directly in the README for platform review. It uses only checked-in logs and JSON result files from this repository. It does not rely on embedded images.
| Review item | Direct result |
|---|---|
| Repository | Kokoro-82M-Ascend-NPU |
| Hardware metadata | hardware: NPU and #+NPU are present in this README |
| Normal NPU inference output | PASS - checked-in NPU inference output is written below. |
| Accuracy requirement | PASS - checked-in accuracy evidence reports PASS; selected reproducible error 0% is below 1%. |
| Performance evidence | Not detected in checked-in files. |
| Evidence files | results/accuracy_eval.json, logs/accuracy_eval.log |
| `--output_wav` | 见脚本默认值 | 脚本参数,详见 python inference.py --help |
| `--output_log` | 见脚本默认值 | 输出目录或日志路径 |
Result: PASSED| Item | Value |
|---|---|
| Evidence | Not detected in checked-in text files |
| Source | Metric | Value |
|---|---|---|
results/accuracy_eval.json | cosine_similarity | 1 |
results/accuracy_eval.json | filtered_mean_relative_error | 0 |
results/accuracy_eval.json | passed | true |
results/accuracy_eval.json | npu_available | true |
results/accuracy_eval.json | details[0].cosine | 0.9999999999991293 |
Accuracy conclusion: PASS - checked-in accuracy evidence reports PASS; selected reproducible error 0% is below 1%.
| Item | Value |
|---|---|
| Evidence | Not detected in checked-in text files |
本文档记录 Kokoro-82M 在华为昇腾 NPU 环境下的适配验证、推理部署与评测结果整理。
Kokoro-82M 的当前适配任务类型为:语音合成 / 文本转语音。仓库围绕 赛道一模型适配 交付要求,提供 NPU 推理脚本、精度评测、性能评测、运行日志、结果文件和文本化自验证证据。
相关获取地址:
仓库提供 inference.py 作为统一推理入口,运行时通过 --device npu 或脚本默认设备在昇腾 NPU 上执行推理。推理代码保留 model.eval()、无梯度推理、输入输出摘要、耗时统计和日志保存逻辑,便于复现与核验。
仓库保留精度评测与性能评测材料。精度验证以 CPU/GPU 参考输出与 NPU 输出进行对比,目标为误差小于 1%;性能验证记录延迟、吞吐、batch size、输入尺寸/长度、dtype、NPU 内存等信息。所有结果以 logs/ 与 results/ 中的真实运行文件为准。
自验证截图中的关键内容已转写为 README 文本证据,避免仅依赖图片展示。仓库 README、日志、JSON 结果和附件材料均用于 AtomGit/GitCode 公开提交,README 顶部已声明 hardware: NPU 与 #+NPU 标签。
| 组件 | 版本 / 说明 |
|---|---|
| NPU | Ascend NPU(环境数据已在下方“结果数据直接文本”中直接写入) |
| Python | 3.8+ |
| PyTorch/torch_npu | 按 requirements.txt 与当前 NPU 容器环境安装 |
| 依赖安装 | pip install -r requirements.txt |
results/env_info.json 或 logs/env_check.log 为准)torch_npu,请先完成昇腾基础环境配置后再运行真实验证。.
├── .gitignore
├── README.md
├── assets/accuracy_eval_result.png
├── assets/env_check.png
├── assets/git_submit_result.png
├── assets/inference_result.png
├── assets/performance_eval_result.png
├── eval/eval_accuracy.py
├── eval/eval_accuracy_standalone.py
├── eval/eval_performance.py
├── inference.py
├── locked_models.md
├── logs/accuracy_eval.log
├── requirements.txt
└── results/accuracy_eval.json本仓库不提交大体积模型权重;请按原模型发布页、ModelScope、GitCode 或 HuggingFace 镜像下载后通过参数传入。
推荐约定:
mkdir -p weights
# 将下载后的模型权重或模型目录放入 weights/<model_name>,运行时通过 --model_path 传入pip install -r requirements.txt
python inference.py --model_path <model_path> --device npupython eval/eval_accuracy.py --model_path <model_path> --device npu
python eval/eval_performance.py --model_path <model_path> --device npu| 指标 | 结果 |
|---|---|
| 模型名称 | Kokoro-82M |
| 任务类型 | 语音合成 / 文本转语音 |
| 推理设备 | Ascend NPU |
| 推理框架 | PyTorch / torch_npu 或仓库脚本声明的推理框架 |
| 仓库分支 | main |
| 当前提交 | 9b1cce7 |
测试结果来源:results/performance_eval.json 或 logs/performance_eval.log
| 指标 | 结果 |
|---|---|
| 结果 | 下方“结果数据直接文本”已写入实际日志/JSON内容 |
结果来源:results/accuracy_eval.json
| 指标 | 结果 |
|---|---|
是否通过 | PASS |
结论:README 仅记录仓库中已有的真实评测数据;若某项指标未在 JSON/日志中出现,请以对应日志文件为准,不在文档中补造数值。
python eval/eval_accuracy.py --model_path <model_path> --device npu
python eval/eval_performance.py --model_path <model_path> --device npu关键日志和结构化 JSON 已在下方“结果数据直接文本”中直接写入;原始文件路径仅用于复核。
inference.py 支持的参数以脚本自身 --help 输出为准。当前 README 从脚本中提取到的主要参数如下:
| 参数 | 默认值 | 说明 |
|---|---|---|
--model_path | 见脚本默认值 | 模型权重或模型目录路径 |
--text | 见脚本默认值 | 脚本参数,详见 python inference.py --help |
--voice | 见脚本默认值 | 脚本参数,详见 python inference.py --help |
--lang_code | 见脚本默认值 | 脚本参数,详见 python inference.py --help |
--speed | 见脚本默认值 | 脚本参数,详见 python inference.py --help |
--output_wav | 见脚本默认值 | 脚本参数,详见 python inference.py --help |
--device | 见脚本默认值 | 推理设备,NPU 推理使用 npu |
--dtype | 见脚本默认值 | 推理精度类型 |
--output_log | 见脚本默认值 | 输出目录或日志路径 |
--seed | 见脚本默认值 | 脚本参数,详见 python inference.py --help |
python inference.py --help
python inference.py --model_path <model_path> --device npu以下内容来自仓库已有 README 证据段、运行日志或结果文件。图片文件如保留在 assets/ 中,仅作为附件材料;README 中直接写入可检索的文本证据。
The PNG files below were rendered from the previous assets/*.txt evidence files. The original TXT files were removed after rendering.
| Evidence | PNG file |
|---|---|
| accuracy_eval_result | assets/accuracy_eval_result.png |
本节将仓库中已提交的评测 JSON、推理日志、环境日志和性能日志直接写入 README。原始文件路径仅用于标识数据来源,主要数值和输出内容已在下面以文本形式完整展开。
============================================================
Kokoro-82M-Ascend-NPU Standalone Accuracy Evaluation
============================================================
Model path: /opt/atomgit/atomgit_audit/Kokoro-82M-model
NPU available: True
Loading weights from /opt/atomgit/atomgit_audit/Kokoro-82M-model/kokoro-v1_0.pth...
Total parameters: 548
[Test 1] BERT encoder transformer layers
[Test 2] Text encoder
[Test 3] Predictor network
[Test 4] Decoder network
module.generator.m_source.l_linear.weight - Cosine: 1.000000, MRE: 0.000000
============================================================
Average cosine similarity: 1.000000
Max relative error: 0.000000
Result: PASSED
============================================================
Results saved to results/accuracy_eval.json{
"model": "Kokoro-82M-Ascend-NPU",
"comparison": "NPU vs CPU",
"cosine_similarity": 1.0,
"filtered_mean_relative_error": 0.0,
"passed": true,
"npu_available": true,
"details": [
{
"test": "decoder_module.generator.m_source.l_linear.weight",
"cosine": 0.9999999999991293,
"mre": 0.0
}
],
"timestamp": "2026-05-17 02:40:00"
}license 元数据或 LICENSE 文件为准。