Instructions to use frankyoujian/EdgeASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- K2
How to use frankyoujian/EdgeASR with K2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
|
Download FFASR.md from frankyoujian/EdgeASR: direct link, hf CLI and curl.
- Browser
- Download file 2.04 kB
-
https://huggingface.co/frankyoujian/EdgeASR/resolve/main/FFASR.md
- Command line
-
hf download hf://frankyoujian/EdgeASR/FFASR.md
-
curl -L -o FFASR.md https://huggingface.co/frankyoujian/EdgeASR/resolve/main/FFASR.md
2.04 kB
| # FFASR offline evaluation | |
| EdgeASR is an **offline/non-streaming English Zipformer RNN-T model**. | |
| It processes the whole recording with a non-causal encoder. Do not select | |
| Streaming ASR for this model. | |
| ## Submission fields | |
| - Model ID: `frankyoujian/EdgeASR` | |
| - Task: offline ASR (`asr` in the API). | |
| - Extra Python requirements: copy the non-comment lines of `requirements.txt`. | |
| - Setup script: leave empty. | |
| - Custom evaluator: copy all of `ffasr_custom_evaluator.py`. | |
| - Contact email: provide your own email directly to FFASR; it is not in this repo. | |
| - Base model: fill only if applicable to the training history. | |
| The custom evaluator pins runtime revision `496a1127c8dd4420e6934f7790cb1ddb33af13b4`. The evaluator loads | |
| the model once, uses FP32 and greedy RNN-T decoding with one symbol per encoder | |
| frame, and exposes the loaded model for parameter counting. Batch size is 1. | |
| There is no external LM or dataset-specific prompt/decoding configuration. | |
| ## Transcript formatting | |
| After BPE reconstruction, `<cap>` capitalizes the preceding word, `<upp>` | |
| uppercases it, and `<.>`, `<,>`, `<?>` become punctuation. Formatting tags are | |
| removed after applying their effects. FFASR applies its own WER normalization | |
| after receiving the formatted transcript. | |
| ```text | |
| we <cap> are from us <upp> <,> and they are from china <cap> <.> who <cap> are they from <?> | |
| ``` | |
| ```text | |
| We are from US, and they are from China. Who are they from? | |
| ``` | |
| ## Reproducibility and validation | |
| `artifact_manifest.json` records SHA-256 hashes of the unchanged checkpoint, | |
| token table, BPE model, configuration, formatter, dependencies and source. | |
| The source snapshot retains its original license under `source/LICENSE`. | |
| Sixteen formatter and production text-return tests passed during preparation, | |
| including actual model token IDs and the exact example above. Dependencies | |
| were resolved for Linux x86-64 / Python 3.12 / CUDA 12.4. Native GPU inference | |
| was not executed as part of package preparation. This document makes no | |
| claim of an official FFASR result. | |