whisper-large-v3-turbo-anv-sot-mlx by Gyori Lab for

Model Card

By Gyori Lab for Computational Biomedicine, published under mit, revision 0d126d19c04c.

An MLX conversion of a Whisper large-v3-turbo fine-tune for Sesotho (Southern Sotho) trained by DSFSI on the African Next Voices corpus. The weights are unchanged apart from the format conversion, for use with Apple silicon. All credit for the model goes to the original authors. Please cite and refer to the source model and the African Next Voices dataset. Whisper has no Sesotho language token. The fine-tune decodes under the English token (en), which Whisper's language detection narrowly picks for it, so pass it explicitly to avoid detection drifting to another language. Turning off conditiononprevioustext avoids repetition loops on long audio. Converted from source revision…

Read Gyori Lab for Computational Biomedicine's full model card

whisper-large-v3-turbo-anv-sot (MLX, float16)

An MLX conversion of dsfsi-anv/whisper-large-v3-turbo-anv-sot, a Whisper large-v3-turbo fine-tune for Sesotho (Southern Sotho) trained by DSFSI on the African Next Voices corpus. The weights are unchanged apart from the format conversion, for use with mlx-whisper on Apple silicon.

All credit for the model goes to the original authors. Please cite and refer to the source model and the African Next Voices dataset.

Usage

Whisper has no Sesotho language token. The fine-tune decodes under the English token (en), which Whisper's language detection narrowly picks for it, so pass it explicitly to avoid detection drifting to another language. Turning off condition_on_previous_text avoids repetition loops on long audio.

import mlx_whisper

result = mlx_whisper.transcribe(
    "audio.wav",
    path_or_hf_repo="gyorilab/whisper-large-v3-turbo-anv-sot-mlx",
    language="en",
    condition_on_previous_text=False,
)
print(result["text"])

Conversion

Converted from source revision 5413ff7b73fd9701831392e18385d90296560a58 with the convert.py script from mlx-examples/whisper and MLX 0.31.2, with --dtype float16. The output model.safetensors is renamed to weights.safetensors, the file name mlx-whisper 0.4 loads.

License

MIT, as for the source model.

Configuration

Model type: whisper

Identity and Version

Repository: gyorilab/whisper-large-v3-turbo-anv-sot-mlx
Publisher: Gyori Lab for Computational Biomedicine
Task: Speech recognition
Modality: Audio
Library: mlx
Parameters: Not stated by the source
Languages: st
Revision: 0d126d19c04c4ebb4d1be6fe63239ab268a58735
First published: 2026-10-09
Last updated: 2026-10-09

Files and Weights

4 files, 1.6 GB in total. The weights are 1 file totalling 1.6 GB in safetensors.

Weights1 file · 1.6 GB

Configuration1 file · 268 B

Documentation1 file · 1.9 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
weights.safetensors	Weights	1.6 GB	6c71a0bf7737
config.json	Configuration	268 B	—
README.md	Documentation	1.9 KB	—
.gitattributes	Repository	1.5 KB	—

License and Download

License: mit
Access: Open weights, no gate
Download size: 1.6 GB

Download from Gyori Lab for Computational Biomedicine

Released by Gyori Lab for Computational Biomedicine through its official repository on Hugging Face. Read the license.

Built From

Derived from dsfsi-anv/whisper-large-v3-turbo-anv-sot

Memory Requirements

Precision	Weights in memory
As published	1.6 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About whisper-large-v3-turbo-anv-sot-mlx

Can I use whisper-large-v3-turbo-anv-sot-mlx commercially?

Yes. whisper-large-v3-turbo-anv-sot-mlx is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Similar Models

Model · Speech recognition

wav2vec2-large-xlsr-53-japanese

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the train and validation splits of Common Voice 6.1, CSS10 and JSUT. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: The model can be evaluated as follows on the Japanese test data of Common Voice. In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the…

Open weights apache-2.0 transformers

View model

Model · Speech recognition

whisperkit-coreml

Argmax

WhisperKit is part of Argmax OSS, an On-device Speech AI SDK for Apple Silicon: https://github.com/argmaxinc/argmax-oss-swift Check out the WhisperKit paper and presentation from ICML 2025: https://icml.cc/virtual/2025/47854 For real-time transcription with speakers and custom vocabulary, check out Argmax Pro SDK: https://www.argmaxinc.com/blog/argmax-sdk-2

Open weights mit whisperkit

View model

Model · Speech recognition

speaker-diarization-3.1

Pyannote

Using this open-source model in production? Consider switching to pyannoteAI for better and faster options. This pipeline is the same as pyannote/speaker-diarization-3.0 except it removes the problematic use of onnxruntime. Both speaker segmentation and embedding now run in pure PyTorch. This should ease deployment and possibly speed up inference. It requires pyannote.audio version 3.1 or higher. It ingests mono audio sampled at 16kHz and outputs speaker diarization as an Annotation instance: - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. - audio files sampled at a different rate are resampled to 16kHz automatically upon loading. 1.…

Access requested at publisher mit pyannote-audio

View model

Model · Speech recognition

speaker-diarization-community-1

Pyannote

This pipeline ingests mono audio sampled at 16kHz and outputs speaker diarization. - stereo or multi-channel audio files are automatically downmixed to mono by averaging the channels. - audio files sampled at a different rate are resampled to 16kHz automatically upon loading. The main improvements brought by Community-1 are: - improved speaker assignment and counting - simpler reconciliation with transcription timestamps with exclusive speaker diarization - easy offline use (i.e. without internet connection) - (optionally) hosted on pyannoteAI cloud 1. pip install pyannote.audio 3. Create access token at hf.co/settings/tokens. Out of the box, Community-1 is much better than…

Access requested at publisher cc-by-4.0 pyannote-audio

View model

Model · Speech recognition

faster-whisper-small

Systran

This repository contains the conversion of openai/whisper-small to the CTranslate2 model format. This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper. The original model was converted with the following command: Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the computetype option in CTranslate2. For more information about the original model, see its model card.

Open weights mit ctranslate2

View model

Model · Speech recognition

wav2vec2-large-xlsr-53-portuguese

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Portuguese using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud:) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint The model can be used directly (without a language model) as follows... Using the HuggingSound library: 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata If you want to cite this model you can use this

Open weights apache-2.0 transformers

View model