# facebook/wav2vec2-base-960h

This model is a speech model pretrained and fine tuned on 960 hours of LibriSpeech audio sampled at 16 kHz. It is used as a standalone acoustic model for transcribing audio files, and the card also shows evaluation on LibriSpeech clean and other test sets.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-facebook-wav2vec2-base-960h
- Citation: facebook/wav2vec2-base-960h. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-facebook-wav2vec2-base-960h (retrieved 2026-11-14).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/files?limit=100. How checks work: https://huggingbay.xyz/verification

## 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/facebook/wav2vec2-base-960h
- Hosting: hosted (10 files)
- Files: 10 hosted of 11 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: 10 hosted of 11 listed
- Full repo upstream: 1.13 GB
- Recommended file: 377.6 MB · model.safetensors
- Download: https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/download-plan)
- Per-file SHA-256: available for 10 of 10 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/files?limit=100
- Availability: Ready
- Downloadable: yes
- 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: 1345601
- Stars: 402
- Card completeness: 96%

## Description

This model is a speech model pretrained and fine tuned on 960 hours of LibriSpeech audio sampled at 16 kHz. It is used as a standalone acoustic model for transcribing audio files, and the card also shows evaluation on LibriSpeech clean and other test sets.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: automatic-speech-recognition
- Library: transformers
- Task categories: automatic-speech-recognition
- Languages: en
- Referenced datasets: librispeech_asr
- Paper ids: 2006.11477
- Model-index entries: wav2vec2-base-960h
- Evaluation signals: 2 model-card eval results
- File hints: 11 upstream file samples

## Evaluation Signals

- LibriSpeech (clean): Test WER = 3.4 (Automatic Speech Recognition)
- LibriSpeech (other): Test WER = 8.6 (Automatic Speech Recognition)

## Referenced Data

- Dataset: librispeech_asr
- Paper: 2006.11477

## File Hints

- .gitattributes (790 B)
- README.md (4.3 KB)
- config.json (1.6 KB)
- feature_extractor_config.json (158 B)
- model.safetensors (360 MB) LFS
- preprocessor_config.json (159 B)
- pytorch_model.bin (360 MB) LFS
- special_tokens_map.json (85 B)
- tf_model.h5 (360 MB) LFS
- tokenizer_config.json (163 B)
- vocab.json (291 B)

## 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 2026-08-28T01:35:06.998Z.
- Open license detected as apache-2.0.
- Model-index metadata found for wav2vec2-base-960h.
- Model card references dataset context: librispeech_asr.
- 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-facebook-wav2vec2-base-960h
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-facebook-wav2vec2-base-960h
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-facebook-wav2vec2-base-960h&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-facebook-wav2vec2-base-960h/decentralized-fallbacks