Downloads · 30 days
1
20% of all-time downloads
ultravox-v0_5-llama-3_2-1b-coreml
aoiandroid/ultravox-v0_5-llama-3_2-1b-coreml
ultravox-v0_5-llama-3_2-1b-coreml is a automatic speech recognition model from aoiandroid. Use it when you need speech turned into text. The card lists the license as mit.
Private Core ML release of Ultravox v0.5 (fixie-ai/ultravox-v05-llama-32-1b) for TranslateBlue on iOS and macOS.
All-time downloads
5
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin6.6 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- mit
- Access
- Public
- Created
- Aug 16, 2026
- Updated
- Sep 1, 2026
- SHA
- 52d936b6
Model card
From the Hugging Face model README
Ultravox v0.5 Llama 3.2 1B (Core ML Native)
Private Core ML release of Ultravox v0.5 (fixie-ai/ultravox-v0_5-llama-3_2-1b) for TranslateBlue on iOS and macOS.
Architecture
- Audio Encoder: Whisper-large-v3-turbo encoder (128 mel bins)
- Projector: SwiGLU 2-layer MLP (1280 → 2048)
- LLM Decoder: Llama-3.2-1B-Instruct with stateful KV cache (
UltravoxLlamaKVCache.mlpackage)
Artifacts
| Path | Role | Notes |
|---|---|---|
AudioEncoder.mlpackage | Encoder source | On-device compile fallback (macOS only) |
AudioEncoder.mlmodelc | Encoder (macOS) | Do not load on iOS |
AudioEncoder-ios.mlmodelc | Encoder (iOS) | Pre-compiled; preferred on iPhone/iPad |
UltravoxLlamaKVCache.mlpackage | Decoder | Stateful Core ML; 2.47 GB weight.bin |
tokenizer.json | BPE tokenizer | Legacy string merges (280,147 entries); required for inference |
tokenizer_config.json | Tokenizer metadata | Not sufficient alone — tokenizer.json is required |
ultravox_llama_kvcache_manifest.json | Decoder manifest | Input/output/state names |
Platform-specific compiled encoder bundles are also published in sibling repos:
Requirements
- iOS 18.0+ or macOS 15.0+
- Physical device required for end-to-end validation — the decoder is a stateful Core ML model (
computeUnits = .cpuAndGPU; ANE unsupported today).
iOS Simulator is not supported
UltravoxLlamaKVCache.mlpackage fails to compile on the iOS Simulator. Observed error:
Espresso exception: "Invalid state": MpsGraph backend validation on incompatible OS
compilation failed — Failed to build the model execution plan … model.mil … error code: -14
Use a physical iPhone or iPad for decoder load and speech-to-text translation tests.
Tokenizer format
tokenizer.json uses the legacy BPE merges string format (["Ġ Ġ", …]), not the tokenizers 0.20+ pair format ([["Ġ","Ġ"], …]). Some Rust tokenizers loaders silently return null on the new format. Byte-level BPE encodes spaces as Ġ, so the string join is unambiguous and reversible.
Tasks
- Direct Speech-to-Text Translation (S2TT)
- Context-Aware Speech Recognition (ASR)
- Voice Conversation / QA
- Task
- Automatic Speech Recognition
- License
- mit
- Created
- Aug 16, 2026
- Updated
- Sep 1, 2026