Instructions to use VoiceScribe/gigaam-v3-e2e-rnnt-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use VoiceScribe/gigaam-v3-e2e-rnnt-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gigaam-v3-e2e-rnnt-mlx VoiceScribe/gigaam-v3-e2e-rnnt-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
| # Upstream Source | |
| This repository is a Voice Scribe **mirror** of an upstream model. The model | |
| weights and code are unchanged from the upstream at the recorded revision. | |
| | Field | Value | | |
| | --- | --- | | |
| | Upstream repo | `aystream/GigaAM-v3-e2e-rnnt-mlx` | | |
| | Upstream revision (sha) | `decfca492069ea30fb5ead79c4516d50c16d93ea` | | |
| | Mirror created | `2026-05-07 12:46:54 UTC` | | |
| | Mirror slug | `gigaam-mlx` | | |
| | Description | GigaAM v3 e2e RNN-T - native MLX / Metal package with punctuation. | | |
| ## Why mirror? | |
| The shipping Voice Scribe installer pins every model to the `voice-scribe/*` | |
| namespace for a single source of truth, integrity check, and future CDN | |
| migration. Upstream repos retain their original license (see | |
| `LICENSE*` / `README*` files preserved unchanged below). | |
| ## Maintenance | |
| When upstream publishes a new revision we want to adopt, run the matching | |
| Voice Scribe mirror script with `--only gigaam-mlx` from the repo root. The script | |
| creates a new commit on this mirror that replaces the snapshot and updates | |
| this `UPSTREAM_SOURCE.md`. | |