# Newmetrics/cohere-transcribe-arabic-07-2026

Model from Hugging Face for automatic speech recognition: Newmetrics/cohere-transcribe-arabic-07-2026 · transformers

## Facts

- Type: Audio
- Task: automatic-speech-recognition
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/Newmetrics/cohere-transcribe-arabic-07-2026
- Hosting: hosted (8 files)
- Files: 8 hosted of 20 listed
- Needs its own code to run: Uses custom model code (configuration_cohere_asr.py). Plain llama.cpp, Ollama and LM Studio commands are not offered for this model unless a GGUF file is listed.
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 8 files, 4.13 GB
- Full repo upstream: 4.13 GB
- Recommended file: 4.13 GB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/download-plan)
- Per-file SHA-256: available for 8 of 8 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 84
- Stars: 0
- Card completeness: 92%

## Description

External Hugging Face catalog record for Newmetrics/cohere-transcribe-arabic-07-2026. Task: automatic speech recognition. Library: transformers. Languages: ar, en. Popularity signal at import: 84 downloads and 0 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: automatic-speech-recognition
- Library: transformers
- Task categories: automatic-speech-recognition
- Languages: ar, en
- File hints: 16 upstream file samples

## File Hints

- .gitattributes (1.6 KB)
- README.md (23 KB)
- config.json (3.3 KB)
- configuration_cohere_asr.py (1.7 KB)
- examples/sample1.wav (111 KB) LFS
- examples/sample2.wav (267 KB) LFS
- generation_config.json (229 B)
- model.safetensors (3.8 GB) LFS
- modeling_cohere_asr.py (63 KB)
- normalizer.json (51 KB)
- preprocessor_config.json (131 B)
- processing_cohere_asr.py (20 KB)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-24T14:38:27.368Z.
- Open license detected as apache-2.0.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-newmetrics-cohere-transcribe-arabic-07-2026
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-newmetrics-cohere-transcribe-arabic-07-2026
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-newmetrics-cohere-transcribe-arabic-07-2026&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-newmetrics-cohere-transcribe-arabic-07-2026/decentralized-fallbacks