whisper-tiny by Joshua: Open-Weight Model

Model Card

By Joshua, published under apache-2.0, revision 5332fcc35e32.

https://huggingface.co/openai/whisper-tiny with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Read Joshua's full model card

https://huggingface.co/openai/whisper-tiny with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

Example: Transcribe audio from a URL.

import { pipeline } from '@huggingface/transformers';

const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny');
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
const output = await transcriber(url);

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Configuration

Architecture: WhisperForConditionalGeneration
Layers: 4
Vocabulary size: 51,865
Model type: whisper

Identity and Version

Repository: Xenova/whisper-tiny
Publisher: Joshua
Task: Speech recognition
Modality: Audio
Library: transformers.js
Parameters: Not stated by the source
Languages: Not stated by the source
Revision: 5332fcc35e32a33b86612b9a57a89be7906102b1
First published: 2023-05-03
Last updated: 2025-12-16

Files and Weights

45 files, 1.9 GB in total. The weights are 31 files totalling 1.9 GB in onnx.

Weights31 files · 1.9 GB

Configuration8 files · 68.9 KB

Tokenizer4 files · 4.3 MB

Documentation1 file · 1.2 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
onnx/decoder_model.onnx	Weights	118.4 MB	d7668e6e5d90
onnx/decoder_model_bnb4.onnx	Weights	86.0 MB	1971aa8a89d2
onnx/decoder_model_fp16.onnx	Weights	59.3 MB	43dbcbd6a54f
onnx/decoder_model_int8.onnx	Weights	110.0 MB	1995c47b14f6
onnx/decoder_model_merged.onnx	Weights	118.6 MB	b81258b0e8ac
onnx/decoder_model_merged_bnb4.onnx	Weights	86.2 MB	ea54ad2b3029
onnx/decoder_model_merged_fp16.onnx	Weights	59.6 MB	b5b6e3f37071
onnx/decoder_model_merged_int8.onnx	Weights	30.7 MB	212f4f045ba7
onnx/decoder_model_merged_q4.onnx	Weights	86.7 MB	462a65ea8459
onnx/decoder_model_merged_q4f16.onnx	Weights	46.0 MB	dc59a0cad1aa
onnx/decoder_model_merged_quantized.onnx	Weights	30.7 MB	6c0c125986b0
onnx/decoder_model_merged_uint8.onnx	Weights	30.7 MB	58152fd4aafc
onnx/decoder_model_q4.onnx	Weights	86.5 MB	ee35f54e2805
onnx/decoder_model_q4f16.onnx	Weights	45.7 MB	22dd644b9fdc
onnx/decoder_model_quantized.onnx	Weights	30.5 MB	d1ac41063dd0
onnx/decoder_model_uint8.onnx	Weights	110.0 MB	ba85d58c9fb0
onnx/decoder_with_past_model.onnx	Weights	113.7 MB	25efcc2a9319
onnx/decoder_with_past_model_bnb4.onnx	Weights	85.3 MB	2cbe80031272
onnx/decoder_with_past_model_fp16.onnx	Weights	56.9 MB	a3229f06de0d
onnx/decoder_with_past_model_int8.onnx	Weights	108.9 MB	22c912aa9a27
onnx/decoder_with_past_model_q4.onnx	Weights	85.8 MB	29a1f511a97e
onnx/decoder_with_past_model_q4f16.onnx	Weights	45.1 MB	39299269a0ab
onnx/decoder_with_past_model_quantized.onnx	Weights	29.2 MB	26d8d7fa7829
onnx/decoder_with_past_model_uint8.onnx	Weights	108.9 MB	3f838b01d502
onnx/encoder_model.onnx	Weights	32.9 MB	39e81b6c86a5
onnx/encoder_model_bnb4.onnx	Weights	8.6 MB	3d9b46e4fe69
onnx/encoder_model_fp16.onnx	Weights	16.5 MB	975ccfeb5cb2
onnx/encoder_model_q4.onnx	Weights	9.0 MB	f895af36f57f
onnx/encoder_model_q4f16.onnx	Weights	6.3 MB	fd605566b1dc
onnx/encoder_model_quantized.onnx	Weights	10.1 MB	fd9d995b9dcb
onnx/encoder_model_uint8.onnx	Weights	10.1 MB	40df112bf7fa
added_tokens.json	Configuration	2.1 KB	—
config.json	Configuration	2.2 KB	—
generation_config.json	Configuration	3.7 KB	—
normalizer.json	Configuration	52.7 KB	—
preprocessor_config.json	Configuration	339 B	—
quant_config.json	Configuration	2.8 KB	—
quantize_config.json	Configuration	2.8 KB	—
special_tokens_map.json	Configuration	2.2 KB	—
README.md	Documentation	1.2 KB	—
.gitattributes	Repository	1.5 KB	—
merges.txt	Tokenizer	493.9 KB	—
tokenizer.json	Tokenizer	2.5 MB	—
tokenizer_config.json	Tokenizer	282.7 KB	—
vocab.json	Tokenizer	1.0 MB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 1.9 GB

Download from Joshua

Released by Joshua through its official repository on Hugging Face. Read the license.

Built From

Derived from openai/whisper-tiny
Quantized from openai/whisper-tiny

Memory Requirements

Precision	Weights in memory
As published	1.9 GB

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

Questions About whisper-tiny

Can I use whisper-tiny commercially?

Yes. whisper-tiny is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

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

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

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

wav2vec2-large-xlsr-53-russian

Jonatas Grosman

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Russian using the train and validation splits of Common Voice 6.1 and CSS10. 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