qc903113684's picture
Simplify global parameters and align developer guidance
eddeb89 verified
|
Raw History Blame Contribute Delete
3.66 kB
---
pipeline_tag: automatic-speech-recognition
base_model: Edge0/Audio8-ASR-Infinite
license: other
license_name: pandora-model-sdk-v1.0
license_link: https://huggingface.co/APLUX-Agora/Audio8-ASR-Infinite-80ms/blob/main/LICENSES/Pandora-Model-SDK.zh-CN.txt
tags:
- pandora
- qualcomm
- qnn
- aidem
---
# Audio8-ASR-Infinite-80ms for Agora
This public repository contains the 80ms streaming ASR package. [Application code and deployment guide](https://github.com/APLUX-Agora/audio8-asr-infinite-demo) are maintained separately. Upstream model: [Edge0/Audio8-ASR-Infinite](https://huggingface.co/Edge0/Audio8-ASR-Infinite).
## Resource layout on main
```text
models.json / agora-model.json / SHA256SUMS
embedding.bin / *.npy / tokenizer.json / token_bytes.json
frontend/ prefix/ semantic_vad/ LICENSES/ NOTICE
targets/
QCS8550/
QCS8625/
IQ8/
IQ9/
```
Common resources are maintained once. Each SoC directory contains its hardware graphs. Branches are not used to select hardware. Model and code releases can be identified with version tags.
## Download with the official Hugging Face CLI
Set only AGORA_WORKSPACE and AGORA_SOC directly in the device terminal. Choose
any workspace path/name. No configuration file transfer is required:
```bash
export AGORA_WORKSPACE="$HOME/my-asr-demo"
export AGORA_SOC='QCS8550'
```
Follow the [five-step deployment guide](https://github.com/APLUX-Agora/audio8-asr-infinite-demo/blob/main/docs/AGORA_DEPLOY.md) to clone code and prepare the environment before downloading resources.
Install huggingface_hub during dependency setup, and activate the project virtual environment once:
```bash
cd "$AGORA_WORKSPACE/code"
source .venv/bin/activate
pip install --upgrade huggingface_hub
```
Keep using this activated terminal. In a new terminal, set the same two variables, change to the code directory, and activate .venv again.
### Download common resources
```bash
hf download APLUX-Agora/Audio8-ASR-Infinite-80ms \
--exclude "targets/*" --local-dir "$AGORA_WORKSPACE/resources"
```
### Download the SoC model
```bash
hf download APLUX-Agora/Audio8-ASR-Infinite-80ms \
--include "targets/$AGORA_SOC/*" --local-dir "$AGORA_WORKSPACE/resources"
```
The default revision is main. Supported AGORA_SOC values: QCS8550, QCS8625, IQ8, IQ9. Public downloads require no token. Re-running the same commands reuses current files and downloads missing or changed files. No Git LFS installation, custom CLI, or sparse checkout is needed. The official [HF CLI guide](https://huggingface.co/docs/huggingface_hub/en/guides/cli) documents this download interface.
A selected package contains about 3.3 GiB of model data. Allow at least 8 GiB for the workspace, dependencies, and download overhead. Use a separate workspace per task or model/hardware combination. Existing unrelated files are not automatically removed.
## Verification and use
```bash
cd "$AGORA_WORKSPACE/resources"
sha256sum -c SHA256SUMS --ignore-missing
cd "$AGORA_WORKSPACE/code"
```
Unselected SoC directories are intentionally absent. The checksum command validates downloaded files; missing-file tolerance alone does not prove completeness. The application's preflight checks required model files and hashes before startup. models.json remains the SDK entry point and owns application defaults. Only QCS8550 / Ubuntu 22.04 has been validated in the Agora lab; other hardware combinations need device qualification.
## License
Original model, SDK, and third-party license terms are unchanged. See LICENSES/ and NOTICE. [Full deployment instructions](https://github.com/APLUX-Agora/audio8-asr-infinite-demo/blob/main/docs/AGORA_DEPLOY.md).