# alvanlii/whisper-small-cantonese

Model from Hugging Face for automatic speech recognition: alvanlii/whisper-small-cantonese · transformers

## Facts

- Type: LLM
- Task: automatic-speech-recognition
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/alvanlii/whisper-small-cantonese
- Hosting: hosted (14 files)
- Files: 14 hosted of 24 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 14 files, 968.7 MB
- Full repo upstream: 5.32 GB
- Recommended file: 5.31 GB (9 files)
- Download: https://huggingbay.xyz/artifact/hf-model-alvanlii-whisper-small-cantonese/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-alvanlii-whisper-small-cantonese/download-plan)
- Per-file SHA-256: available for 14 of 14 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-alvanlii-whisper-small-cantonese/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 361258
- Stars: 118
- Card completeness: 96%

## Description

External Hugging Face catalog record for alvanlii/whisper-small-cantonese. Task: automatic speech recognition. Library: transformers. Languages: zh, yue. Datasets referenced by card metadata: mozilla-foundation/common_voice_16_0, mozilla-foundation/common_voice_17_0. Base model: openai/whisper-small. Includes 1 model-card evaluation signal. Popularity signal at import: 219,329 downloads and 118 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: automatic-speech-recognition
- Library: transformers
- Base model: openai/whisper-small
- Task categories: automatic-speech-recognition
- Languages: zh, yue
- Referenced datasets: mozilla-foundation/common_voice_16_0, mozilla-foundation/common_voice_17_0
- Paper ids: 2201.02419
- Model-index entries: Whisper Small zh-HK - Alvin
- Evaluation signals: 1 model-card eval result
- File hints: 16 upstream file samples

## Evaluation Signals

- mozilla-foundation/common_voice_16_0 yue: Normalized CER = 7.93 (Automatic Speech Recognition)

## Referenced Data

- Dataset: mozilla-foundation/common_voice_16_0
- Dataset: mozilla-foundation/common_voice_17_0
- Paper: 2201.02419

## File Hints

- .gitattributes (1.4 KB)
- README.md (5.5 KB)
- added_tokens.json (2.1 KB)
- config.json (2.3 KB)
- cts/config.json (4.2 KB)
- cts/model.bin (922 MB) LFS
- cts/preprocessor_config.json (339 B)
- cts/vocabulary.json (1.0 MB)
- generation_config.json (4.2 KB)
- ggml-model.bin (465 MB) LFS
- merges.txt (482 KB)
- model.safetensors (922 MB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-07-29T22:22:20.062Z.
- Open license detected as apache-2.0.
- Model-index metadata found for Whisper Small zh-HK - Alvin.
- Model card references dataset context: mozilla-foundation/common_voice_16_0, mozilla-foundation/common_voice_17_0.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-alvanlii-whisper-small-cantonese
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-alvanlii-whisper-small-cantonese/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-alvanlii-whisper-small-cantonese/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-alvanlii-whisper-small-cantonese/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-alvanlii-whisper-small-cantonese
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-alvanlii-whisper-small-cantonese/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-alvanlii-whisper-small-cantonese&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-alvanlii-whisper-small-cantonese/decentralized-fallbacks