Skip to content
ModelListedExternal
Download

Wav2vec2 Base 960h GGUF

GGUF conversion of facebook/wav2vec2-base-960h for CrispASR.

Sourcehuggingface.co/cstr/wav2vec2-base-960h-GGUF/tree/7c025ea07cffc65b211b360e5865dfe59df7e8af
KindOtherBase modelfacebook/wav2vec2-base-960hVersionRevision 7c025ea

Model source

Kind
Other
File size
197 MB
Base model
facebook/wav2vec2-base-960h
Version
vRevision 7c025ea
Updated
Sep 18, 2026
Downloads
21
Source
Hugging Face

Source description

wav2vec2-base-960h — GGUF

GGUF conversion of facebook/wav2vec2-base-960h for CrispASR.

This model is primarily used as a CTC forced aligner — it produces word-level timestamps by aligning a known transcript to audio. It can also perform standalone ASR via CTC greedy decode.

Architecture

  • wav2vec2-base: 12-layer transformer encoder (768-dim, 12 heads)
  • CTC head: Linear(768, 32) — character-level English vocabulary
  • Feature extractor: 7-layer CNN (raw waveform -> 512-dim features)
  • Input: 16 kHz mono audio
  • Training: 960 hours of LibriSpeech (supervised CTC fine-tune)

Files

FileSizeDescription
wav2vec2-base-960h.gguf197 MBFull precision (F16 weights, F32 norms)

Usage with CrispASR

Forced alignment (word-level timestamps)

# Align a transcript to audio — produces word-level SRT:
crispasr --align-only \
    -am wav2vec2-base-960h.gguf \
    -f audio.wav \
    --ref-text "The quick brown fox jumps over the lazy dog." \
    --align-format srt --align-output aligned.srt

# Or align from an existing SRT (re-time the cues):
crispasr --align-only \
    -am wav2vec2-base-960h.gguf \
    -f audio.wav \
    --text-file subtitles.srt \
    --align-output retimed.srt

As an aligner companion for LLM ASR backends

# Word timestamps for any backend that lacks native ones:
crispasr --backend granite -m auto \
    -am wav2vec2-base-960h.gguf --force-aligner \
    -f audio.wav -osrt

Auto-download

# The aligner is auto-downloaded when using -am auto:
crispasr --backend granite -m auto \
    -am auto --force-aligner \
    -f audio.wav -osrt

License

Apache 2.0 (same as the original model).

Credits

Provenance and EU AI Act Art. 53 note

  • Upstream model: facebook/wav2vec2-base-960h — published by facebook.
  • Upstream licence: apache-2.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
  • What was done here: format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
  • Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
  • Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.

Sources

1 source
Hugging FacePrimaryVersion 7c025ea07cffc65b211b360e5865dfe59df7e8af
huggingface.co/cstr/wav2vec2-base-960h-GGUF/tree/7c025ea07cffc65b211b360e5865dfe59df7e8af

Verified Sep 7

Model artifacts

1 artifact

wav2vec2-base-960h.gguf

gguf · 197 MB · SHA-256 298d900e7159…3cf7 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 7huggingface.co/cstr/wav2vec2-base-960h-GGUF

--- language: en license: apache-2.0 tags: - gguf - asr - speech-recognition - ctc - forced-alignment - wav2vec2 - crispasr base_model: facebook/wav2vec2-base-960h pipeline_tag: automatic-speech-recognition --- # wav2vec2-base-960h — GGUF GGUF conversion of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) for [CrispASR](https://github.com/CrispStrobe/CrispASR). This model is primarily used as a **CTC forced aligner** — it produces word-level timestamps by aligning a known transcript to audio. It can also perform standalone ASR via CTC greedy decode. ## Architecture - **wav2vec2-base**: 12-layer transformer encoder (768-dim, 12 heads) - **CTC head**: Linear(768, 32) — character-level English vocabulary - **Feature extractor**: 7-layer CNN (raw waveform -> 512-dim features) - **Input**: 16 kHz mono audio - **Training**: 960 hours of LibriSpeech (supervised CTC fine-tune) ## Files | File | Size | Description | |------|------|-------------| | `wav2vec2-base-960h.gguf` | 197 MB | Full precision (F16 weights, F32 norms) | ## Usage with CrispASR ### Forced alignment (word-level timestamps) ```bash # Align a transcript to audio — produces word-level SRT: crispasr --align-only \ -am wav2vec2-base-960h.gguf \ -f audio.wav \ --ref-text "The quick brown fox jumps over the lazy dog." \ --align-format srt --align-output aligned.srt # Or align from an existing SRT (re-time the cues): crispasr --align-only \ -am wav2vec2-base-960h.gguf \ -f audio.wav \ --text-file subtitles.srt \ --align-output retimed.srt ``` ### As an aligner companion for LLM ASR backends ```bash # Word timestamps for any backend that lacks native ones: crispasr --backend granite -m auto \ -am wav2vec2-base-960h.gguf --force-aligner \ -f audio.wav -osrt ``` ### Auto-download ```bash # The aligner is auto-downloaded when using -am auto: crispasr --backend granite -m auto \ -am auto --force-aligner \ -f audio.wav -osrt ``` ## License Apache 2.0 (same as the original model). ## Credits - Original model: [Facebook AI / Meta](https://huggingface.co/facebook/wav2vec2-base-960h) - GGUF conversion & runtime: [CrispASR](https://github.com/CrispStrobe/CrispASR) ## Provenance and EU AI Act Art. 53 note - **Upstream model:** [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) — published by `facebook`. - **Upstr...

NoteSep 7huggingface.co/cstr/wav2vec2-base-960h-GGUF

Source context: 21 downloads · 1 likes · Pipeline automatic-speech-recognition · Repo cstr/wav2vec2-base-960h-GGUF