LiveNew tools this week

cohere-transcribe-coreml-fp16

phequals/cohere-transcribe-coreml-fp16

cohere-transcribe-coreml-fp16 is a machine learning model from phequals. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

Corrected CoreML FP16 release of CohereLabs/cohere-transcribe-03-2026 for Apple Silicon inference.

Downloads · 30 days

1

1% of all-time downloads

All-time downloads

111

Public

Repo size

8.1 GB

Likes

1

Public

Repo makeup

Click a slice to open those files.

.bin4.3 GB · 100%

At a glance

License: apache-2.0
Access: Public
Created: Mar 27, 2026
Updated: Mar 28, 2026
SHA: b5542923

Base models

CohereLabs/cohere-transcribe-03-2026

Model card

From the Hugging Face model README

Cohere Transcribe — CoreML FP16

Corrected CoreML FP16 release of CohereLabs/cohere-transcribe-03-2026 for Apple Silicon inference.

This release uses:

a length-aware encoder with inputs mel and length
decoder prefill and decode models with explicit encoder_mask inputs
verified token IDs: pad=2, eos=3, bos=4

The March 28 encoder fix preserves the real mel length at inference time, which avoids the padding-related repetition and hallucination issues seen with the older static encoder export.

Contents

Artifact	Precision	Notes
`cohere_encoder.mlpackage`	FP16	Length-aware encoder (`mel`, `length`)
`cohere_decoder_prefill.mlpackage`	FP16	Prompt prefill with `encoder_mask`
`cohere_decoder_decode.mlpackage`	FP16	Single-token decode with `encoder_mask`

Inputs / Outputs

Encoder

Input	Shape	Type
`mel`	`[1, 128, 3500]`	float32
`length`	`[1]`	int32

Output	Shape	Type
`encoder_hidden`	`[1, 438, 1024]`	float16

Decoder Prefill

Input	Shape	Type
`encoder_hidden`	`[1, 438, 1024]`	float32
`input_ids`	`[1, 10]`	int32
`encoder_mask`	`[1, 438]`	float32

Decoder Decode

Input	Shape	Type
`input_ids`	`[1, 1]`	int32
`cache_update_mask`	`[1, 512]`	float32
`cache_valid_mask`	`[1, 512]`	float32
`encoder_mask`	`[1, 438]`	float32

Prompt

English transcription with punctuation uses the token IDs:

[13764, 7, 4, 16, 62, 62, 5, 9, 11, 13]

Relevant tokenizer IDs:

pad_token_id = 2
eos_token_id = 3
bos_token_id = 4

Validation

The corrected encoder was validated in Apple CoreML runtime with the same padded mel input and different length values:

same-length repeat max diff: 0.0
full-vs-short length max diff: 2.988

License

Apache 2.0 (same as the base model)

License: apache-2.0
Created: Mar 27, 2026
Updated: Mar 28, 2026