Cohere Transcribe 2B

Esta página da Soniqo documenta Cohere Transcribe 2B conforme a implementação local em speech-swift / speech-core. Os links do Hugging Face ficam abaixo das notas de integração.

Página interna primeiro

Cards e menus apontam primeiro para cá; os links do modelo fonte e dos bundles continuam disponíveis nesta página.

Visão geral

Modelo	Cohere Transcribe 2B
Papel	High-accuracy multilingual offline speech-to-text
Backend	Native MLX on Apple Silicon
Saída	Plain-text transcription
Idiomas	14 languages
Licença	Apache-2.0
Status	Published FP16, INT5, and INT8 bundles; INT5 is the default
Fonte	Cohere Transcribe
Produto Swift	`CohereTranscribeASR`
CLI / runtime	`speech transcribe --engine cohere`

Uso

O trecho abaixo reflete a API ou comando atual exposto por speech-swift.

# INT5 is the default.
speech transcribe recording.wav --engine cohere

# Select another published precision and pass a language hint.
speech transcribe recording.wav --engine cohere --model int8 --language de

Links do modelo

Notas de implementação

The runtime resamples mono Float32 PCM to 16 kHz and handles long recordings in overlapping chunks.
INT5 is the practical default: on the validated English FLEURS run it used a 1.62 GiB bundle, 2,582 MiB physical footprint, and 0.0150 mean RTF.
MLX affine quantization supports 2, 3, 4, 5, 6, and 8 bits, not INT7; choose INT8 when prioritizing quality.
This is a non-streaming engine. The CLI rejects --stream instead of silently changing behavior.
The published benchmark covers English read speech and does not claim parity with conversational, telephone, noisy, or speaker-heavy benchmarks.