{"v":1,"id":"model:hf:christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF","slug":"model-christopherthompson81-vibevoice-asr-streaming-1-5b-gguf","kind":"model","category":"speech","title":"VibeVoice-ASR-Streaming-1.5B-GGUF","summary":"VibeVoice ASR Streaming 1.5B GGUF for audio.cpp","source":{"provider":"hf","ref":"christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF","url":"https://huggingface.co/christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF","rev":"ff96151102990984d6d0e951e62751bdb2ff9243","fetchedAt":"2026-10-09T19:01:09.410Z","etag":"W/\"802-JNV2u6GRBpHFUwVAqxgPECngzY8\""},"author":{"name":"christopherthompson81","url":"https://huggingface.co/christopherthompson81"},"license":{"spdx":"mit","raw":"mit","open":true},"metrics":{"downloads":39182,"downloadsWeek":15664,"likes":0,"stars":54249,"openIssues":352,"lastRelease":{"tag":"v1.9.5","at":"2026-10-06T17:39:17Z"},"pushedAt":"2026-10-06T17:39:15Z","takenAt":"2026-10-09T19:01:09.410Z"},"tags":["gguf","audio.cpp","asr","streaming","speaker-attributed-transcription","automatic-speech-recognition","en","zh","es","pt","de","ja","ko","fr","ru","it"],"pipeline":"automatic-speech-recognition","links":{"github":"ggml-org/whisper.cpp","npm":"nodejs-whisper"},"updatedAt":"2026-09-20T00:43:17.000Z","collectedAt":"2026-10-09T19:01:09.410Z","review":{"numbers":["39,182 downloads on Hugging Face","0 likes","license mit","3.1 GB for vibevoice-asr-streaming-1.5b-q8_0.gguf","54,249 stars on ggml-org/whisper.cpp","352 open issues and PRs","last release v1.9.5 on 2026-10-06","15,664 npm downloads a week for nodejs-whisper","latest nodejs-whisper@0.3.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-09T19:01:09.410Z","http":200},"description":"# VibeVoice ASR Streaming 1.5B GGUF for audio.cpp\n\nThis repository contains audio.cpp-native GGUF builds of\n`microsoft/VibeVoice-ASR-Streaming-1.5B`.\n\nThe 1.5B checkpoint runs through the same audio.cpp loader as the 7B with no\ncode changes: the layer count, hidden size, and head counts are read from the\ncheckpoint's own `config.json`, and the tensor names are identical.\n\n## Use with audio.cpp\n\nInstall the recommended Q8_0 package through the audio.cpp model manager:\n\n```bash\npython3 tools/model_manager_v2.py install vibevoice_asr_streaming_1_5b_q8_0\n```\n\nRun offline ASR:\n\n```bash\nbuild/debug/bin/audiocpp_cli \\\n  --task asr \\\n  --family vibevoice_asr_streaming \\\n  --model models/VibeVoice-ASR-Streaming-1.5B-GGUF/vibevoice-asr-streaming-1.5b-q8_0.gguf \\\n  --backend cuda \\\n  --threads 8 \\\n  --audio input.wav \\\n  --text-out transcript.txt \\\n  --metrics \\\n  --log\n```\n\nRun the server with the model loaded:\n\n```json\n{\n  \"host\": \"127.0.0.1\",\n  \"port\": 8080,\n  \"backend\": \"cuda\",\n  \"threads\": 8,\n  \"models\": [\n    {\n      \"id\": \"vibevoice-streaming-1.5b\",\n      \"family\": \"vibevoice_asr_streaming\",\n      \"path\": \"models/VibeVoice-ASR-Streaming-1.5B-GGUF/vibevoice-asr-streaming-1.5b-q8_0.gguf\",\n      \"task\": \"asr\",\n      \"mode\": \"streaming\"\n    }\n  ]\n}\n```\n\nThen start the server:\n\n```bash\nbuild/debug/bin/audiocpp_server --config server.json --log\n```\n\nFor live streaming, send 16 kHz mono signed 16-bit PCM to the live endpoint:\n\n```bash\nffmpeg -hide_banner -loglevel error -i input.wav -f s16le -ac 1 -ar 16000 - \\\n  | curl -N -X POST \\\n      -H 'Content-Type: application/octet-stream' \\\n      -H 'Transfer-Encoding: chunked' \\\n      -H 'Expect:' \\\n      -T - \\\n      'http://127.0.0.1:8080/v1/audio/transcriptions/live?model=vibevoice-streaming-1.5b&sample_rate=16000&channels=1&sample_format=s16le'\n```\n\n## Files\n\n| File | Format | Notes |\n|---|---|---|\n| `vibevoice-asr-streaming-1.5b-bf16.gguf`…\n\nSource: https://huggingface.co/christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF","install":{"kind":"model","hfId":"christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF","gated":false,"format":"gguf","files":[{"name":"vibevoice-asr-streaming-1.5b-bf16.gguf","size":5644319488,"quant":"BF16","sha256":"431c2308213db5cd02d715e39c36556fa3705244fe17806195ec8727504d16bc"},{"name":"vibevoice-asr-streaming-1.5b-q4_k.gguf","size":2117525248,"quant":"Q4_K","sha256":"2a2d8abf2d4f7d3a127b34002895b3c9fa7a97ccf5e175c90071c1224fb771cb"},{"name":"vibevoice-asr-streaming-1.5b-q8_0.gguf","size":3343199488,"quant":"Q8_0","sha256":"1a92c0f6c72439d58dedaaff96bb77264802618bd577f58cc0176f47bae5180d"}],"totalBytes":11105044224,"suggestedFile":"vibevoice-asr-streaming-1.5b-q8_0.gguf","requirements":{"ramGb":5,"diskBytes":3343199488,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"],"command":"lsh models install hf:christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF"}}