From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.speechSubject: whisper-small-asr-fp16 Date: 2026-11-15Commit: 42fc41cSigned: 2DC28CC7B26A283B ✓ Automatic speech recognition model with 241M parameters. Safetensors weights, 486 MB in all. Published by mlx-community under Apache-2.0.
241M params 486 MB whisper-small-asr-fp16 safetensors permissive Facts Params 241M Size 486 MB Formats safetensors Task automatic speech recognition License Apache-2.0 permissive
fw
$ fw get mlx-community/whisper-small-asr-fp16
# manifest sha256 fe6325348e5e… · 486 MB · 14 files
$ fw verify ./whisper-small-asr-fp16 mlx-community/whisper-small-asr-fp16Hosted (signed) mlx-community/whisper-small-asr-fp16 Last check: 2026-11-15 03:36 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24
Overview
Size 486 MB
Weights 481 MB (safetensors)
Parameters 241M
Formats safetensors
Task automatic speech recognition
License Apache-2.0 (permissive)
Files 14, each with a sha256
Publisher mlx-community
Added 2026-11-15
Section alt.freeweights.speech Lineage
Original release from the publisher.
Where these bytes come from
Publisher at the pinned commit →You
Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge Host Last check Result huggingface.co 2026-11-15 03:36 UTC passed
Model card From the publisher at commit
42fc41c . Shown as plain text with links; images open at the publisher.
This model was converted to MLX format from openai/whisper-small0.2.10 . Refer to the original model card for more details on the model.
Use with mlx-audio#
pip install -U mlx-audioCLI Example:#
python -m mlx_audio.stt.generate --model mlx-community/whisper-small-asr-fp16 --audio "audio.wav"Python Example:#
from mlx_audio.stt.utils import load_model
from mlx_audio.stt.generate import generate_transcription
model = load_model("mlx-community/whisper-small-asr-fp16")
transcription = generate_transcription(
model=model,
audio_path="path_to_audio.wav",
output_path="path_to_output.txt",
format="txt",
verbose=True,
)
print(transcription.text) Files 14 files · 486 MB Weights 481 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 3.17 KB bc5bb7346fcd7c429315fc004b90a79c3bf0c162148bb15a913257d7f83fb0ca added_tokens.json 34.6 KB 9715fd2243b6f06a5858b5e32950d2853f73dd5bc201aafcf76f5082a2d8acd1 config.json 2.42 KB 88e2c5b3af9eb9afaade1c616c09fd6fe71d6d5b32867a15e9d70ce817a4c36f generation_config.json 3.87 KB 71565b8ef50d0bf7a1193ed4bbed195b94e70c18894d81bba2f1233dcec3ab53 merges.txt 494 KB 2df2990a395e35e8dfbc7511e08c12d56018d8d04691e0133e5d63b21e154dc6 model.safetensors 481 MB 24358337a2c8f19675e40cb6db8a82d73d1ca97dca4484a4e6c19daeb1d30f55 model.safetensors.index.json 31.1 KB 95c8953795aea944994325013cb0f3fdbb0fa85494d4583695452a62254293ed normalizer.json 52.7 KB bf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd preprocessor_config.json 185 KB 9b5cd03a36fbb8a627c64d98a5b5b126ead95a77720723944487311f0110b666 special_tokens_map.json 2.19 KB e67ae3a0aaa99abcd9f187138e12db1f65c16a14761c50ef10eef2c174a7a691 tokenizer.json 2.48 MB 27fc476bfe7f17299480be2273fc0608e4d5a99aba2ab5dec5374b4482d1a566 tokenizer_config.json 283 KB 2a4c4281cf9f51ac6ccc406fdc711a087afe6530f671fa7b80953edc498275ce vocab.json 836 KB 8f680bba319e01a653d2e8a5dbc17a9157179e0576e6ce74ce0c06356c6e24f9
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 42fc41c2ab pinned now 2026-11-15 03:36 UTC 14 files · 486 MB
Use it fw
$ fw get mlx-community/whisper-small-asr-fp16
# manifest sha256 fe6325348e5e… · 486 MB · 14 files
$ fw verify ./whisper-small-asr-fp16 mlx-community/whisper-small-asr-fp16fw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/whisper-small-asr-fp16.json --dir ./whisper-small-asr-fp16
$ python3 fw.py verify ./whisper-small-asr-fp16 ./mlx-community__whisper-small-asr-fp16.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/whisper-small-asr-fp16 --revision 42fc41c2ab1c78e844fd01477cf398eec6801c47 --local-dir ./whisper-small-asr-fp16transformers Speech recognition with the transformers pipeline.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import pipeline
asr = pipeline("automatic-speech-recognition", model="mlx-community/whisper-small-asr-fp16", revision="42fc41c2ab1c78e844fd01477cf398eec6801c47")
print(asr("audio.wav")["text"])License Name Apache License 2.0 Id Apache-2.0 Class Permissive Redistribution yes Listing Hosted (signed) Decided License as declared by the publisher. No person read it. 2026-11-15 Text in README.md Text sha256 bc5bb7346fcd7c429315fc004b90a79c3bf0c162148bb15a913257d7f83fb0ca Terms gate No extra terms beyond the license. Read the license text
Licenses are checked against the license table . A custom license passes only after a person reads it.
Provenance From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.speechSubject: whisper-small-asr-fp16 Date: 2026-11-15Commit: 42fc41cSigned: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/whisper-small-asr-fp16.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/whisper-small-asr-fp16.json.minisig
$ minisign -Vm whisper-small-asr-fp16.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download
Model tree No related models in this catalog. Nothing here lists this model as its parent, and it names no parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/whisper-small-asr-fp16Open in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
87M params 693 MB ast-finetuned-audioset-10-10-0.4593 safetensors permissive Facts Params 87M Size 693 MB Formats safetensors Task audio classification License BSD-3-Clause permissive flip From: MIT <huggingface.co/MIT> Subject: ast-finetuned-audioset-10-10-0.4593 speech 958 MB ast-finetuned-audioset-10-10-0.4593-ONNX onnx permissive Facts Params not stated Size 958 MB Formats onnx Task audio classification License BSD-3-Clause permissive flip From: <huggingface.co/onnx-community> Subject: ast-finetuned-audioset-10-10-0.4593-ONNX 601M params 2.57 GB Audio8-TTS-Preview-0.6b safetensors permissive Facts Params 601M Size 2.57 GB Formats safetensors Task text to speech License Apache-2.0 permissive flip From: Edge0 <huggingface.co/Edge0> Subject: Audio8-TTS-Preview-0.6b 601M params 2.57 GB Audio8-TTS-Realistic-Air safetensors permissive Facts Params 601M Size 2.57 GB Formats safetensors Task text to speech License Apache-2.0 permissive flip From: Edge0 <huggingface.co/Edge0> Subject: Audio8-TTS-Realistic-Air 104M params 831 MB audiobox-aesthetics safetensors permissive Facts Params 104M Size 831 MB Formats safetensors Task audio classification License CC-BY-4.0 permissive flip From: facebook <huggingface.co/facebook> Subject: audiobox-aesthetics 693M params 612 MB chatterbox-4bit safetensors permissive Facts Params 693M Size 612 MB Formats safetensors Task text to speech License Apache-2.0 permissive flip From: <huggingface.co/mlx-community> Subject: chatterbox-4bit
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.speechSubject: 
onnx-community