# openai/whisper-medium

Model from Hugging Face for automatic speech recognition: openai/whisper-medium · transformers

## Facts

- Type: Audio
- 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/openai/whisper-medium
- Hosting: hosted (16 files)
- Files: 16 hosted of 16 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: at least 16 listed files; full count and size unknown
- Full repo upstream: 12.2 GB
- Recommended file: 3.06 GB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-openai-whisper-medium/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-openai-whisper-medium/download-plan)
- Per-file SHA-256: available for 9 of 16 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-openai-whisper-medium/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: 406246
- Stars: 291
- Card completeness: 96%

## Description

External Hugging Face catalog record for openai/whisper-medium. Task: automatic speech recognition. Library: transformers. Languages: en, zh, de, es, ru, ko, fr, ja. Includes 3 model-card evaluation signals. Popularity signal at import: 355,192 downloads and 291 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: automatic-speech-recognition
- Library: transformers
- Task categories: automatic-speech-recognition
- Languages: en, zh, de, es, ru, ko, fr, ja
- Paper ids: 2212.04356
- Model-index entries: whisper-medium
- Evaluation signals: 3 model-card eval results
- File hints: 16 upstream file samples

## Evaluation Signals

- LibriSpeech (clean): Test WER = 2.9 (Automatic Speech Recognition)
- LibriSpeech (other): Test WER = 5.9 (Automatic Speech Recognition)
- Common Voice 11.0: Test WER = 53.87 (Automatic Speech Recognition)

## Referenced Data

- Paper: 2212.04356

## File Hints

- .gitattributes (1.4 KB)
- README.md (19 KB)
- added_tokens.json (34 KB)
- config.json (1.9 KB)
- flax_model.msgpack (2.8 GB) LFS
- generation_config.json (3.7 KB)
- merges.txt (482 KB)
- model.safetensors (2.8 GB) LFS
- normalizer.json (51 KB)
- preprocessor_config.json (181 KB)
- pytorch_model.bin (2.8 GB) LFS
- special_tokens_map.json (2.1 KB)

## 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 2026-07-29T22:22:15.011Z.
- Open license detected as apache-2.0.
- Model-index metadata found for whisper-medium.
- 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-openai-whisper-medium
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-openai-whisper-medium/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-openai-whisper-medium/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-openai-whisper-medium/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-openai-whisper-medium
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-openai-whisper-medium/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-openai-whisper-medium&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-openai-whisper-medium/decentralized-fallbacks