Skip to page content
SAVRN
Search Plan a project

Open-weight model · Speech recognition

RK182X-ASR-SeaCo-Paraformer

by RKNNAI RKNNAI/RK182X-ASR-SeaCo-Paraformer

RK182X-ASR-SeaCo-Paraformer is an open-weight model for speech recognition from RKNNAI, released under Apache License 2.0. Its published files total 662.0 MB.

本仓库提供由 iic/speechseacoparaformerlargeasrnat-zh-cn-16k-common-vocab8404-pytorch 转换得到的 RKNN ASR 模型。 - Model ID：RKNNAI/RK182X-ASR-SeaCo-Paraformer - 模型显示名称：RK182X-ASR-SeaCo-Paraformer - 源模型：iic/speechseacoparaformerlargeasrnat-zh-cn-16k-common-vocab8404-pytorch…

Parameters—
Context—
Weights34.0 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By RKNNAI, published under apache-2.0, revision 1ba08faa1ed1.

本仓库提供由 iic/speechseacoparaformerlargeasrnat-zh-cn-16k-common-vocab8404-pytorch 转换得到的 RKNN ASR 模型。 - Model ID：RKNNAI/RK182X-ASR-SeaCo-Paraformer - 模型显示名称：RK182X-ASR-SeaCo-Paraformer - 源模型：iic/speechseacoparaformerlargeasrnat-zh-cn-16k-common-vocab8404-pytorch - 模型类型：ASR ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - CIF 和 BiasEncoder 组件在 CPU 上运行。 源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。 本发布物为源模型的 RKNN 转换/量化衍生物，保留原始许可与归属声明，见 Notice。

Read RKNNAI's full model card

1. 模型介绍

本仓库提供由 iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch 转换得到的 RKNN ASR 模型。

  • Model ID：RKNNAI/RK182X-ASR-SeaCo-Paraformer
  • 模型显示名称：RK182X-ASR-SeaCo-Paraformer
  • 发布版本：v1.1.0
  • 源模型：iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
  • 模型类型：ASR
  • 芯片字段：RK182X
  • 具体支持芯片：RK1820、RK1828

可用模型

发布版本 配置目录 支持芯片 量化方式 NPU 核数
v1.1.0 SeaCo-Paraformer-fp16-1 RK1820、RK1828 paraformer_encoder: fp16；paraformer_decoder: fp16；paraformer_decoder_hotword: fp16；seaco_decoder: fp16；asf_scorer: fp16 paraformer_encoder: 1；paraformer_decoder: 1；paraformer_decoder_hotword: 1；seaco_decoder: 1；asf_scorer: 1

2. 文件说明

文件或目录 说明
LICENSE 源模型许可证
Notice 许可、使用要求及归属说明
<配置目录>/ 配套模型文件
子目录 README.md 当前配置说明
子目录 config.json 模型配置与文件清单
子目录 SHA256SUMS 当前目录交付文件的 SHA-256 校验值（不包含自身）

3. 模型下载

ModelScope 完整下载：

modelscope download --model RKNNAI/RK182X-ASR-SeaCo-Paraformer --revision v1.1.0 --local_dir ./RK182X-ASR-SeaCo-Paraformer

Hugging Face 完整下载：

hf download RKNNAI/RK182X-ASR-SeaCo-Paraformer --revision v1.1.0 --local-dir ./RK182X-ASR-SeaCo-Paraformer

ModelScope 指定配置下载：

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK182X-ASR-SeaCo-Paraformer",
    revision="v1.1.0",
    allow_patterns=["README.md", "LICENSE", "Notice", "SeaCo-Paraformer-fp16-1/**"],
    local_dir="./RK182X-ASR-SeaCo-Paraformer",
)

Hugging Face 指定配置下载：

hf download RKNNAI/RK182X-ASR-SeaCo-Paraformer --revision v1.1.0 --include "README.md" "LICENSE" "Notice" "SeaCo-Paraformer-fp16-1/**" --local-dir ./RK182X-ASR-SeaCo-Paraformer

4. SHA-256 校验

在配置目录执行：

cd ./RK182X-ASR-SeaCo-Paraformer/SeaCo-Paraformer-fp16-1
sha256sum -c SHA256SUMS

所有条目显示 OK 后再部署。

5. 兼容性与限制

  • 支持芯片：RK1820、RK1828。
  • 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。
  • 所选配置目录内的文件须配套使用。
  • CIF 和 BiasEncoder 组件在 CPU 上运行。

6. 版权与许可证

源模型许可证见根目录 LICENSE；同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

本发布物为源模型的 RKNN 转换/量化衍生物，保留原始许可与归属声明，见 Notice。

Identity and Version

Repository
RKNNAI/RK182X-ASR-SeaCo-Paraformer
Publisher
RKNNAI
Task
Speech recognition
Modality
Audio
Library
Not stated by the source
Parameters
Not stated by the source
Languages
asr
Revision
1ba08faa1ed164cc28847073a53cf229ec991731
First published
2026-09-24
Last updated
2026-09-28

Files and Weights

26 files, 662.0 MB in total. The weights are 1 file totalling 34.0 MB in bin.

Weights1 file · 34.0 MB
Configuration2 files · 113.4 KB
Documentation4 files · 18.0 KB
Other18 files · 627.8 MB
Repository1 file · 2.4 KB
Every file
FileTypeSizeSHA-256
SeaCo-Paraformer-fp16-1/bias_encoder.binWeights34.0 MB f3fa2ce155e3
SeaCo-Paraformer-fp16-1/config.jsonConfiguration19.7 KB —
SeaCo-Paraformer-fp16-1/tokens.jsonConfiguration93.7 KB —
LICENSEDocumentation11.4 KB —
NoticeDocumentation414 B —
README.mdDocumentation3.1 KB —
SeaCo-Paraformer-fp16-1/README.mdDocumentation3.1 KB —
SeaCo-Paraformer-fp16-1/SHA256SUMSOther1.9 KB —
SeaCo-Paraformer-fp16-1/asf_scorer-model_report.htmlOther77.4 KB —
SeaCo-Paraformer-fp16-1/asf_scorer.rknnOther257.8 KB e644b6f227af
SeaCo-Paraformer-fp16-1/asf_scorer.weightOther24.9 MB 02a085227b2b
SeaCo-Paraformer-fp16-1/hotwords.txtOther10 B —
SeaCo-Paraformer-fp16-1/paraformer_decoder-model_report.htmlOther103.6 KB —
SeaCo-Paraformer-fp16-1/paraformer_decoder.rknnOther2.2 MB 939b88e0c7ee
SeaCo-Paraformer-fp16-1/paraformer_decoder.weightOther114.3 MB e20611d37e2e
SeaCo-Paraformer-fp16-1/paraformer_decoder_hotword-model_report.htmlOther107.3 KB —
SeaCo-Paraformer-fp16-1/paraformer_decoder_hotword.rknnOther2.2 MB 26016cfd8e92
SeaCo-Paraformer-fp16-1/paraformer_decoder_hotword.weightOther114.3 MB e20611d37e2e
SeaCo-Paraformer-fp16-1/paraformer_encoder-model_report.htmlOther90.9 KB —
SeaCo-Paraformer-fp16-1/paraformer_encoder.rknnOther3.6 MB f1e5446b6078
SeaCo-Paraformer-fp16-1/paraformer_encoder.weightOther319.0 MB ea6f2897495f
SeaCo-Paraformer-fp16-1/seaco_decoder-model_report.htmlOther109.1 KB —
SeaCo-Paraformer-fp16-1/seaco_decoder.rknnOther1.9 MB 2d1b1fd54154
SeaCo-Paraformer-fp16-1/seaco_decoder.weightOther36.5 MB 3db3dd2a654e
SeaCo-Paraformer-fp16-1/seg_dictOther8.3 MB —
.gitattributesRepository2.4 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
34.0 MB
Download from RKNNAI

Released by RKNNAI through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published34.0 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About RK182X-ASR-SeaCo-Paraformer

Can I use RK182X-ASR-SeaCo-Paraformer commercially?

Yes. RK182X-ASR-SeaCo-Paraformer is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Speech recognition

wav2vec2-large-xlsr-53-japanese

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the train and validation splits of Common Voice 6.1, CSS10 and JSUT. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: The model can be evaluated as follows on the Japanese test data of Common Voice. In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the…

Open weights apache-2.0 transformers
View model

Model · Speech recognition

whisperkit-coreml

Argmax

WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854 For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2

Open weights mit whisperkit
View model

Model · Speech recognition

speaker-diarization-3.1

Pyannote

Using this open-source model in production? Consider switching to pyannoteAI for better and faster options. This pipeline is the same as pyannote/speaker-diarization-3.0 except it removes the problematic use of onnxruntime. Both speaker segmentation and embedding now run in pure PyTorch. This should ease deployment and possibly speed up inference. It requires pyannote.audio version 3.1 or higher. It ingests mono audio sampled at 16kHz and outputs speaker diarization as an Annotation instance: - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. - audio files sampled at a different rate are resampled to 16kHz automatically upon loading. 1.…

Access requested at publisher mit pyannote-audio
View model

Model · Speech recognition

speaker-diarization-community-1

Pyannote

This pipeline ingests mono audio sampled at 16kHz and outputs speaker diarization. - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. - audio files sampled at a different rate are resampled to 16kHz automatically upon loading. The main improvements brought by Community-1 are: - improved speaker assignment and counting - simpler reconciliation with transcription timestamps with exclusive speaker diarization - easy offline use (i.e. without internet connection) - (optionally) hosted on pyannoteAI cloud 1. pip install pyannote.audio 3. Create access token at hf.co/settings/tokens. Out of the box, Community-1 is much better than…

Access requested at publisher cc-by-4.0 pyannote-audio
View model

Model · Speech recognition

faster-whisper-small

Systran

This repository contains the conversion of openai/whisper-small to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper. The original model was converted with the following command: Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the computetype option in CTranslate2. For more information about the original model, see its model card.

Open weights mit ctranslate2
View model

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Portuguese using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata If you want to cite this model you can use this

Open weights apache-2.0 transformers
View model