Skip to page content
SAVRN
Search Plan a project

Open-weight model · Speech recognition

moonshine-streaming-small-en

by Inference4j - Java library for onnx models inference4j/moonshine-streaming-small-en

moonshine-streaming-small-en is an open-weight model for speech recognition from Inference4j - Java library for onnx models, released under MIT License. Its published files total 143.7 MB.

Moonshine v2 streaming small speech recognition model for English, quantized to ONNX Runtime (.ort) format for efficient on-device transcription. Mirrored for use with inference4j, an inference-only AI library for Java.

Parameters—
Context—
Weights143.7 MB
Licensemit
AccessOpen weights
Monthly Downloads—

Model Card

By Inference4j - Java library for onnx models, published under mit, revision 50c7b57f2cd0.

Moonshine v2 streaming small speech recognition model for English, quantized to ONNX Runtime (.ort) format for efficient on-device transcription. Mirrored for use with inference4j, an inference-only AI library for Java. This model is licensed under the MIT License. Original models by Moonshine AI.

Read Inference4j - Java library for onnx models's full model card

Moonshine Streaming (Small) — ONNX Runtime (.ort)

Moonshine v2 streaming small speech recognition model for English, quantized to ONNX Runtime (.ort) format for efficient on-device transcription.

Mirrored for use with inference4j, an inference-only AI library for Java.

Original Source

Usage with inference4j

try (var recognizer = MoonshineRecognizer.builder()
        .modelId("inference4j/moonshine-streaming-small-en")
        .build()) {
    RecognitionResult result = recognizer.recognize(audioStream);
    System.out.println(result.text());
}

Model Details

Property Value
Architecture Moonshine v2 Streaming (Small)
Release quantized_26_08_21
Task Streaming automatic speech recognition
Precision Quantized (.ort)
Language English (en)
Limits At most 30 s per call (hard graph limit: 4096 frames / ~82 s)

License

This model is licensed under the MIT License. Original models by Moonshine AI.

Limits

  • Language: English only.
  • Audio duration: At most 30 s per call; use SegmentedSpeechRecognizer for longer audio.
  • Graph frame limit: Hard limit inside the graphs is 4096 frames (about 82 s).

Identity and Version

Repository
inference4j/moonshine-streaming-small-en
Publisher
Inference4j - Java library for onnx models
Task
Speech recognition
Modality
Audio
Library
onnx
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
50c7b57f2cd0301cc2983c7fb11e991b1e599d10
First published
2026-10-13
Last updated
2026-10-13

Files and Weights

10 files, 143.7 MB in total.

Configuration1 file · 512 B
Tokenizer1 file · 1.7 MB
Documentation1 file · 1.7 KB
Other6 files · 142.1 MB
Repository1 file · 1.8 KB
Every file
FileTypeSizeSHA-256
streaming_config.jsonConfiguration512 B —
README.mdDocumentation1.7 KB —
adapter.ortOther2.9 MB c665f742364f
cross_kv.ortOther5.4 MB e2d3417144e9
decoder_kv.ortOther81.9 MB 1a05465b1dd9
encoder.ortOther44.1 MB 2d4d973e91e8
frontend.model.ortOther26.9 KB —
frontend.weights.ortOther7.8 MB 7ef97521bd4b
.gitattributesRepository1.8 KB —
tokenizer.jsonTokenizer1.7 MB —

License and Download

License
mit
Access
Open weights, no gate
Download from Inference4j - Java library for onnx models

Released by Inference4j - Java library for onnx models through its official repository on Hugging Face. Read the license.

Questions About moonshine-streaming-small-en

Can I use moonshine-streaming-small-en commercially?

Yes. moonshine-streaming-small-en 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

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