Cohere Transcribe Arabic 07 2026 GGUF

--- license: apache-2.0 base_model: CohereLabs/cohere-transcribe-arabic-07-2026 base_model_relation: quantized library_name: transcribe.cpp pipeline_tag: automatic-speech-recognition language: - ar - en tags: - gguf - transcribe.cpp - asr - speech-to-text - cohere - conformer - encoder-decoder - arabic transcribe_cpp: wer_fleurs_ar_test: bf16: 11.02 f16: 11.0 q8_0: 11.06 q6_k: 11.07 q5_k_m: 10.95 q4_k_m: 11.18 rtf_m4_max: metal: 73 cpu: 9 rtf_ryzen_4750u: vulkan: 8 cpu: 3 streaming: false translate: false lang_detect: false timestamps: none --- # cohere-transcribe-arabic-07-2026: transcribe.cpp GGUF GGUF conversions of [CohereLabs/cohere-transcribe-arabic-07-2026](https://huggingface.co/CohereLabs/cohere-transcribe-arabic-07-2026) for use with [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp). Ported from upstream commit [0a8193c](https://huggingface.co/CohereLabs/cohere-transcribe-arabic-07-2026/commit/0a8193c), pinned 2026-07-07. Validated against the Transformers reference at transcribe.cpp commit [d89ecb7](https://github.com/handy-computer/transcribe.cpp/tree/d89ecb7) on 2026-07-07. Offline Arabic speech-to-text, including dialectal Arabic and Arabic-English code-switching, with English as a secondary language. An Arabic-focused adaptation of the Cohere Transcribe 03-2026 architecture: a Conformer encoder with a Transformer encoder-decoder head (cross-attention, tied token embedding). Takes a 16 kHz mono WAV and a language flag (`-l ar` or `-l en`) and produces a transcript. Decoding is autoregressive. ## Downloads | Quantization | Download | Size | WER (FLEURS Arabic test) | | --- | --- | ---: | ---: | | BF16 | [cohere-transcribe-arabic-07-2026-BF16.gguf](https://huggingface.co/handy-computer/cohere-transcribe-arabic-07-2026-gguf/resolve/main/cohere-transcribe-arabic-07-2026-BF16.gguf) | 4.10 GB | 11.02% | | F16 | [cohere-transcribe-arabic-07-2026-F16.gguf](https://huggingface.co/handy-computer/cohere-transcribe-arabic-07-2026-gguf/resolve/main/cohere-transcribe-arabic-07-2026-F16.gguf) | 4.11 GB | 11.00% | | Q8_0 | [cohere-transcribe-arabic-07-2026-Q8_0.gguf](https://huggingface.co/handy-computer/cohere-transcribe-arabic-07-2026-gguf/resolve/main/cohere-transcribe-arabic-07-2026-Q8_0.gguf) | 2.41 GB | 11.06% | | Q6_K | [cohere-transcribe-arabic-07-2026-Q6_K.gguf](https://huggingface.co/handy-computer...