anonymous1121/CAFE_ASR

AI model by anonymous1121

Open original source ↗

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Anonymous model repository for the ARR submission "CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition". CAFE-25lang is the 25-language CAFE model of the paper (CAFE (ours) in its tables). It is a compact FastConformer-TDT transducer distilled from Parakeet-TDT-0.6B-v3. CAFE (Confined-Adapter Feature distillation) sends the CKA feature-distillation gradient only into language-routed adapters that English bypasses, so the shared encoder never receives it. language gate adds 0.495M (0.19%). structured pruning of the 627M teacher. applied to non-English utterances only. Languages (25): Bulgarian (bg), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hungarian (hu), Italian (it), Latvian (lv), Lithuanian (lt), Maltese (mt), Polish (pl), Portuguese (pt), Romanian (ro), Russian (ru), Slovak (sk), Slovenian (sl), Spanish (es), Swedish (sv), Ukrainian (uk). Install the dependencies; audio must be 16 kHz mono WAV: CAFE routes by language: English runs…

anonymous1121/CAFE_ASR on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-16T01:48:18.751Z

Inside the original model card — Document outline
  1. CAFE-25lang
  2. Files
  3. Usage
  4. 1. Without the gate: language known
  5. 2. With the gate: language unknown
  6. Results
  7. Comparison with external systems
  8. Main comparison: Open ASR Leaderboard
  9. Adapter overhead
  10. Routing and the language gate
  11. Per-dataset results
  12. Evaluation

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

anonymous1121/CAFE_ASR is a task-unspecified model repository published by anonymous1121 on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
Not reported
Library
Not reported
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
Not reported — check the model card
Access
Not gated by Hugging Face
Created
2026-10-02T06:13:36.000Z
Last modified
2026-10-02T06:13:36.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-02T06:39:29.113Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models