aufklarer/Cohere-Transcribe-2B-MLX-8bit

Cohere Transcribe 2B — MLX 8-bit affine

MLX weights for Cohere Transcribe 2B, ready for local speech-to-text with speech-swift.

Parameters	Precision	Sample rate	Languages
2B	8-bit affine	16 kHz	14

Files

File	Description
model*.safetensors	MLX model weights
config.json	Model and runtime configuration
tokenizer.model and tokenizer JSON files	SentencePiece tokenizer data

Usage

speech transcribe recording.wav --engine cohere --model int8

import CohereTranscribeASR

let model = try await CohereTranscribeModel.load(
    "aufklarer/Cohere-Transcribe-2B-MLX-8bit"
)
let text = model.transcribe(
    audio: samples,
    sampleRate: sourceSampleRate,
    language: "en"
)

Benchmark

English FLEURS read speech, 80 utterances (759.56 seconds), Apple M5 Pro:

Variant	Bundle	WER	Mean RTF	Peak RSS
FP16	3.85 GiB	6.178%	0.0444	3,964 MiB
INT5	1.62 GiB	6.288%	0.0150	1,776 MiB
INT8	2.25 GiB	6.178%	0.0159	2,428 MiB

These read-speech measurements are not Artificial Analysis Conversational or ElevenLabs Scribe results.

Source and license

The base model is CohereLabs/cohere-transcribe-03-2026 and is released under Apache 2.0.

Links

• Cohere Transcribe guide
• speech-swift
• Soniqo documentation
• Soniqo
• Blog