cstr/wav2vec2-large-xlsr-53-english-gguf - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
cstr/wav2vec2-large-xlsr-53-english-gguf overview
GGUF conversion of jonatasgrosman/wav2vec2-large-xlsr-53-english for English speech recognition.
Downloads
147
Likes
0
Pipeline
automatic-speech-recognition
Library
ggml
Visibility
Public
Access
Open
Repository Files & Downloads
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "apache-2.0",
"tags": [
"automatic-speech-recognition",
"wav2vec2",
"gguf",
"crispasr",
"english"
],
"base_model": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
"pipeline_tag": "automatic-speech-recognition",
"library_name": "ggml",
"language": [
"en"
],
"frontmatter": {
"license": "apache-2.0",
"tags": [
"automatic-speech-recognition",
"wav2vec2",
"gguf",
"crispasr",
"english"
],
"base_model": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
"pipeline_tag": "automatic-speech-recognition",
"library_name": "ggml",
"language": [
"en"
]
},
"hero_image_url": "",
"summary": "GGUF conversion of jonatasgrosman/wav2vec2-large-xlsr-53-english for English speech recognition.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: apache-2.0\ntags:\n - automatic-speech-recognition\n - wav2vec2\n - gguf\n - crispasr\n - english\nbase_model: jonatasgrosman/wav2vec2-large-xlsr-53-english\npipeline_tag: automatic-speech-recognition\nlibrary_name: ggml\nlanguage:\n - en\n---\n\n# Wav2Vec2 Large XLSR-53 English — GGUF\n\nGGUF conversion of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) for English speech recognition.\n\n## Model details\n\n| Property | Value |\n|---|---|\n| Architecture | Wav2Vec2 (CNN feature extractor + 24 Transformer layers) |\n| Hidden size | 1024 |\n| Attention heads | 16 |\n| CTC vocabulary | 33 tokens |\n| Format | GGUF (F16 weights) |\n| Size | 627 MB |\n\nThe model was pre-trained on 53 languages (XLSR-53) and fine-tuned on English Common Voice data with a CTC head. It accepts 16 kHz mono audio and outputs character-level transcriptions.\n\n## Usage with CrispASR\n\n```bash\ncrispasr \\\n --backend wav2vec2 \\\n -m wav2vec2-xlsr-en.gguf \\\n audio.wav\n```\n\n## Provenance\n\nWeights were converted from the original Hugging Face PyTorch checkpoint into GGUF format with F16 precision for all transformer and feature-extractor parameters.\n\n## License\n\nApache-2.0 — same as the original model.\n",
"related_quantizations": []
},
"tags": [
"ggml",
"gguf",
"automatic-speech-recognition",
"wav2vec2",
"crispasr",
"english",
"en",
"base_model:jonatasgrosman/wav2vec2-large-xlsr-53-english",
"base_model:quantized:jonatasgrosman/wav2vec2-large-xlsr-53-english",
"license:apache-2.0",
"region:us"
],
"likes": 0,
"downloads": 147,
"gated": false,
"private": false,
"last_modified": "2026-04-12T14:48:31.000Z",
"created_at": "2026-04-12T14:06:44.000Z",
"pipeline_tag": "automatic-speech-recognition",
"library_name": "ggml"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69dba6f4e48aad1702f3f9c9",
"id": "cstr/wav2vec2-large-xlsr-53-english-GGUF",
"modelId": "cstr/wav2vec2-large-xlsr-53-english-GGUF",
"sha": "3de5f69700e163286eaae85952fba9bf4ab761f6",
"createdAt": "2026-04-12T14:06:44.000Z",
"lastModified": "2026-04-12T14:48:31.000Z",
"author": "cstr",
"downloads": 147,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "automatic-speech-recognition",
"library_name": "ggml",
"siblings_count": 6
}