Duplicate from UsefulSensors/moonshine-tiny-ja

Co-authored-by: Adam Sabra <theadamsabra@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,173 @@
+ MOONSHINE AI COMMUNITY LICENSE AGREEMENT 
+ 
+ Last Updated: June 15th, 2025
+
+
+I. INTRODUCTION
+
+This Agreement applies to any individual person or entity ("You", "Your" or
+"Licensee") that uses or distributes any portion or element of the Moonshine AI
+Materials or Derivative Works thereof for any Research & Non-Commercial or
+Commercial purpose. Capitalized terms not otherwise defined herein are defined
+in Section V below.
+
+
+This Agreement is intended to allow research, non-commercial, and limited
+commercial uses of the Models free of charge. In order to ensure that certain
+limited commercial uses of the Models continue to be allowed, this Agreement
+preserves free access to the Models for people or organizations generating
+annual revenue of less than US $1,000,000 (or local currency equivalent). 
+
+
+By clicking "I Accept" or by using or distributing or using any portion or
+element of the Moonshine Materials or Derivative Works, You agree that You have
+read, understood and are bound by the terms of this Agreement. If You are acting
+on behalf of a company, organization or other entity, then "You" includes you
+and that entity, and You agree that You: (i) are an authorized representative of
+such entity with the authority to bind such entity to this Agreement, and (ii)
+You agree to the terms of this Agreement on that entity's behalf. 
+
+II. RESEARCH & NON-COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement, Moonshine AI grants You a non-exclusive,
+worldwide, non-transferable, non-sublicensable, revocable and royalty-free
+limited license under Moonshine AI's intellectual property or other rights owned
+by Moonshine AI embodied in the Moonshine AI Materials to use, reproduce,
+distribute, and create Derivative Works of, and make modifications to, the
+Moonshine AI Materials for any Research or Non-Commercial Purpose. "Research
+Purpose" means academic or scientific advancement, and in each case, is not
+primarily intended for commercial advantage or monetary compensation to You or
+others. "Non-Commercial Purpose" means any purpose other than a Research Purpose
+that is not primarily intended for commercial advantage or monetary compensation
+to You or others, such as personal use (i.e., hobbyist) or evaluation and
+testing. 
+
+III. COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement (including the remainder of this Section
+III), Moonshine AI grants You a non-exclusive, worldwide, non-transferable,
+non-sublicensable, revocable and royalty-free limited license under Moonshine
+AI's intellectual property or other rights owned by Moonshine AI embodied in the
+Moonshine AI Materials to use, reproduce, distribute, and create Derivative
+Works of, and make modifications to, the Moonshine AI Materials for any
+Commercial Purpose. "Commercial Purpose" means any purpose other than a Research
+Purpose or Non-Commercial Purpose that is primarily intended for commercial
+advantage or monetary compensation to You or others, including but not limited
+to, (i) creating, modifying, or distributing Your product or service, including
+via a hosted service or application programming interface, and (ii) for Your
+business's or organization's internal operations. If You are using or
+distributing the Moonshine AI Materials for a Commercial Purpose, You must
+register with Moonshine AI at (https://moonshine.ai/community-license). If at
+any time You or Your Affiliate(s), either individually or in aggregate, generate
+more than USD $1,000,000 in annual revenue (or the equivalent thereof in Your
+local currency), regardless of whether that revenue is generated directly or
+indirectly from the Moonshine AI Materials or Derivative Works, any licenses
+granted to You under this Agreement shall terminate as of such date. You must
+request a license from Moonshine AI at (https://moonshine.ai/license) , which
+Moonshine AI may grant to You in its sole discretion. If you receive Moonshine
+AI Materials, or any Derivative Works thereof, from a Licensee as part of an
+integrated end user product, then Section III of this Agreement will not apply
+to you.
+
+IV. GENERAL TERMS
+
+Your Research, Non-Commercial, and Commercial License(s) under this Agreement
+are subject to the following terms. a. Distribution & Attribution. If You
+distribute or make available the Moonshine AI Materials or a Derivative Work to
+a third party, or a product or service that uses any portion of them, You shall:
+(i) provide a copy of this Agreement to that third party, (ii) retain the
+following attribution notice within a "Notice" text file distributed as a part
+of such copies: "This Moonshine AI Model is licensed under the Moonshine AI
+Community License, Copyright © Moonshine AI Ltd. All Rights Reserved", and (iii)
+prominently display "Powered by Moonshine AI" on a related website, user
+interface, blogpost, about page, or product documentation. If You create a
+Derivative Work, You may add your own attribution notice(s) to the "Notice" text
+file included with that Derivative Work, provided that You clearly indicate
+which attributions apply to the Moonshine AI Materials and state in the "Notice"
+text file that You changed the Moonshine AI Materials and how it was modified.
+b. Use Restrictions. Your use of the Moonshine AI Materials and Derivative
+Works, including any output or results of the Moonshine AI Materials or
+Derivative Works, must comply with applicable laws and regulations (including
+Trade Control Laws and equivalent regulations) and adhere to the Documentation
+and Moonshine AI's AUP, which is hereby incorporated by reference. Furthermore,
+You will not use the Moonshine AI Materials or Derivative Works, or any output
+or results of the Moonshine AI Materials or Derivative Works, to create or
+improve any foundational generative AI model (excluding the Models or Derivative
+Works). c. Intellectual Property. (i) Trademark License. No trademark licenses
+are granted under this Agreement, and in connection with the Moonshine AI
+Materials or Derivative Works, You may not use any name or mark owned by or
+associated with Moonshine AI or any of its Affiliates, except as required under
+Section IV(a) herein. (ii) Ownership of Derivative Works. As between You and
+Moonshine AI, You are the owner of Derivative Works You create, subject to
+Moonshine AI's ownership of the Moonshine AI Materials and any Derivative Works
+made by or for Moonshine AI. (iii) Ownership of Outputs. As between You and
+Moonshine AI, You own any outputs generated from the Models or Derivative Works
+to the extent permitted by applicable law. (iv) Disputes. If You or Your
+Affiliate(s) institute litigation or other proceedings against Moonshine AI
+(including a cross-claim or counterclaim in a lawsuit) alleging that the
+Moonshine AI Materials, Derivative Works or associated outputs or results, or
+any portion of any of the foregoing, constitutes infringement of intellectual
+property or other rights owned or licensable by You, then any licenses granted
+to You under this Agreement shall terminate as of the date such litigation or
+claim is filed or instituted. You will indemnify and hold harmless Moonshine AI
+from and against any claim by any third party arising out of or related to Your
+use or distribution of the Moonshine AI Materials or Derivative Works in
+violation of this Agreement. (v) Feedback. From time to time, You may provide
+Moonshine AI with verbal and/or written suggestions, comments or other feedback
+related to Moonshine AI's existing or prospective technology, products or
+services (collectively, "Feedback"). You are not obligated to provide Moonshine
+AI with Feedback, but to the extent that You do, You hereby grant Moonshine AI a
+perpetual, irrevocable, royalty-free, fully-paid, sub-licensable, transferable,
+non-exclusive, worldwide right and license to exploit the Feedback in any manner
+without restriction. Your Feedback is provided "AS IS" and You make no
+warranties whatsoever about any Feedback. d. Disclaimer Of Warranty. UNLESS
+REQUIRED BY APPLICABLE LAW, THE MOONSHINE AI MATERIALS AND ANY OUTPUT AND
+RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY
+KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
+OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR
+PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OR
+LAWFULNESS OF USING OR REDISTRIBUTING THE MOONSHINE AI MATERIALS, DERIVATIVE
+WORKS OR ANY OUTPUT OR RESULTS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF
+THE MOONSHINE AI MATERIALS, DERIVATIVE WORKS AND ANY OUTPUT AND RESULTS. e.
+Limitation Of Liability. IN NO EVENT WILL MOONSHINE AI OR ITS AFFILIATES BE
+LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE,
+PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST
+PROFITS OR ANY DIRECT, INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY
+OR PUNITIVE DAMAGES, EVEN IF MOONSHINE AI OR ITS AFFILIATES HAVE BEEN ADVISED OF
+THE POSSIBILITY OF ANY OF THE FOREGOING. f. Term And Termination. The term of
+this Agreement will commence upon Your acceptance of this Agreement or access to
+the Moonshine AI Materials and will continue in full force and effect until
+terminated in accordance with the terms and conditions herein. Moonshine AI may
+terminate this Agreement if You are in breach of any term or condition of this
+Agreement. Upon termination of this Agreement, You shall delete and cease use of
+any Moonshine AI Materials or Derivative Works. Section IV(d), (e), and (g)
+shall survive the termination of this Agreement. g. Governing Law. This
+Agreement will be governed by and constructed in accordance with the laws of the
+United States and the State of California without regard to choice of law
+principles, and the UN Convention on Contracts for International Sale of Goods
+does not apply to this Agreement.
+
+V. DEFINITIONS 
+
+"Affiliate(s)" means any entity that directly or indirectly controls, is
+controlled by, or is under common control with the subject entity; for purposes
+of this definition, "control" means direct or indirect ownership or control of
+more than 50% of the voting interests of the subject entity. "Agreement" means
+this Moonshine AI Community License Agreement. "AUP" means the Moonshine AI
+Acceptable Use Policy available at https://moonshine.ai/use-policy, as may be
+updated from time to time. "Derivative Work(s)" means (a) any derivative work of
+the Moonshine AI Materials as recognized by U.S. copyright laws and (b) any
+modifications to a Model, and any other model created which is based on or
+derived from the Model or the Model's output, including"fine tune" and "low-rank
+adaptation" models derived from a Model or a Model's output, but do not include
+the output of any Model. "Documentation" means any specifications, manuals,
+documentation, and other written information provided by Moonshine AI related to
+the Software or Models. "Model(s)" means, collectively, Moonshine AI's
+proprietary models and algorithms, including machine-learning models, trained
+model weights and other elements of the foregoing. "Moonshine AI" or "we" means
+Moonshine AI Ltd. and its Affiliates. "Software" means Moonshine AI's
+proprietary software made available under this Agreement now or in the future. "
+Moonshine AI Materials" means, collectively, Moonshine's proprietary Models,
+Software and Documentation (and any portion or combination thereof) made
+available under this Agreement. "Trade Control Laws" means any applicable U.S.
+and non-U.S. export control and trade sanctions laws and regulations.

README.md

@@ -0,0 +1,117 @@
+---
+language:
+- ja
+library_name: transformers
+license: other
+pipeline_tag: automatic-speech-recognition
+arxiv: https://arxiv.org/abs/2509.02523
+---
+
+# Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
+
+[[Paper]](https://huggingface.co/papers/2509.02523) [[Code]](https://github.com/moonshine-ai/moonshine) [[Installation]](https://github.com/usefulsensors/moonshine/blob/main/README.md)
+
+This is the model card for running the automatic speech recognition (ASR) models (Moonshine models) trained and released by Moonshine AI (f.k.a Useful Sensors.)
+
+Following [Model Cards for Model Reporting (Mitchell et al.)](https://arxiv.org/abs/1810.03993), we're providing some information about the automatic speech recognition model. More information on how these models were trained and evaluated can be found [in the paper](https://arxiv.org/abs/2509.02523). Note, a lot of the text has been copied verbatim from the [model card](https://github.com/openai/whisper/blob/main/model-card.md) for the Whisper model developed by OpenAI, because both models serve identical purposes, and carry identical risks.
+
+## Usage
+
+Moonshine is supported in Hugging Face 🤗 Transformers. To run the model, first install the Transformers library. For this example, we'll also install 🤗 Datasets to load toy audio dataset from the Hugging Face Hub, and 🤗 Accelerate to reduce the model loading time:
+
+```bash
+pip install --upgrade pip
+pip install --upgrade transformers datasets[audio]
+```
+
+```python
+from transformers import MoonshineForConditionalGeneration, AutoProcessor
+from datasets import load_dataset, Audio
+import torch
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model = MoonshineForConditionalGeneration.from_pretrained('UsefulSensors/moonshine-tiny-ja').to(device).to(torch_dtype)
+processor = AutoProcessor.from_pretrained('UsefulSensors/moonshine-tiny-ja')
+
+dataset = load_dataset('UsefulSensors/multilingual_examples', split='ja')
+dataset = dataset.cast_column("audio", Audio(processor.feature_extractor.sampling_rate))
+sample = dataset[0]["audio"]
+
+inputs = processor(
+    sample["array"], 
+    return_tensors="pt",
+    sampling_rate=processor.feature_extractor.sampling_rate
+)
+inputs = inputs.to(device, torch_dtype)
+
+# to avoid hallucination loops, we limit the maximum length of the generated text based expected number of tokens per second
+token_limit_factor = 13 / processor.feature_extractor.sampling_rate 
+seq_lens = inputs.attention_mask.sum(dim=-1)
+max_length = int((seq_lens * token_limit_factor).max().item())
+
+generated_ids = model.generate(**inputs, max_length=max_length)
+print(processor.decode(generated_ids[0], skip_special_tokens=True))
+```
+
+## Model Details
+
+This Moonshine model is trained for the speech recognition task, capable of transcribing Japanese speech audio into Japanese text. Moonshine AI developed the models to support their business direction of developing real time speech transcription products based on low cost hardware. The following table shows comparisons of common ASR evaluations sets. For more information about evaluation, please refer to the paper.
+
+| Size | Parameters | Fleurs (CER) ↓ | Common Voice 17 (CER) ↓ |
+|:----:|:----------:|:------------------:|:------------------:|
+| whisper tiny | 39 M       | 47.2                  | 96.11                    |
+| whisper medium | 769 M       |  11.5                 | 29.09                 |
+| moonshine tiny | 27 M       |           17.87        | 18.3                  |
+
+### Release date
+
+September 2025
+
+### Model type
+
+Sequence-to-sequence ASR (automatic speech recognition) and speech translation model
+
+## Model Use
+
+### Evaluated Use
+
+The primary intended users of these models are AI developers that want to deploy Japanese speech recognition systems in platforms that are severely constrained in memory capacity and computational resources. We recognize that once models are released, it is impossible to restrict access to only “intended” uses or to draw reasonable guidelines around what is or is not safe use.
+
+The models are primarily trained and evaluated on Arabic ASR task. They may exhibit additional capabilities, particularly if fine-tuned on certain tasks like voice activity detection, speaker classification, or speaker diarization but have not been robustly evaluated in these areas. We strongly recommend that users perform robust evaluations of the models in a particular context and domain before deploying them.
+
+In particular, we caution against using Moonshine models to transcribe recordings of individuals taken without their consent or purporting to use these models for any kind of subjective classification. We recommend against use in high-risk domains like decision-making contexts, where flaws in accuracy can lead to pronounced flaws in outcomes. The models are intended to transcribe Japanese speech, use of the model for classification is not only not evaluated but also not appropriate, particularly to infer human attributes.
+
+## Training Data
+
+The models are trained on 53,900 hours of audio and the corresponding transcripts collected from the internet, as well as datasets openly available and accessible on HuggingFace. The open datasets used are listed in the [the accompanying paper](https://arxiv.org/abs/2509.02523).
+
+## Performance and Limitations
+
+Our evaluations show that, the models exhibit greater accuracy on standard datasets over existing ASR systems of both similar and larger sizes. 
+
+However, like any machine learning model, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
+
+In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. It is likely that this behavior and hallucinations may be worse for short audio segments, or segments where parts of words are cut off at the beginning or the end of the segment.
+
+## Broader Implications
+
+We anticipate that Moonshine models’ transcription capabilities may be used for improving accessibility tools, especially for real-time transcription. The real value of beneficial applications built on top of Moonshine models suggests that the disparate performance of these models may have real economic implications.
+
+There are also potential dual-use concerns that come with releasing Moonshine. While we hope the technology will be used primarily for beneficial purposes, making ASR technology more accessible could enable more actors to build capable surveillance technologies or scale up existing surveillance efforts, as the speed and accuracy allow for affordable automatic transcription and translation of large volumes of audio communication. Moreover, these models may have some capabilities to recognize specific individuals out of the box, which in turn presents safety concerns related both to dual use and disparate performance. In practice, we expect that the cost of transcription is not the limiting factor of scaling up surveillance projects.
+
+## Citation
+If you benefit from our work, please cite us:
+
+```
+@misc{king2025flavorsmoonshinetinyspecialized,
+      title={Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices}, 
+      author={Evan King and Adam Sabra and Manjunath Kudlur and James Wang and Pete Warden},
+      year={2025},
+      eprint={2509.02523},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2509.02523}, 
+}
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "MoonshineForConditionalGeneration"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "decoder_hidden_act": "silu",
+  "decoder_num_attention_heads": 8,
+  "decoder_num_hidden_layers": 6,
+  "decoder_num_key_value_heads": 8,
+  "decoder_start_token_id": 1,
+  "encoder_hidden_act": "gelu",
+  "encoder_num_attention_heads": 8,
+  "encoder_num_hidden_layers": 6,
+  "encoder_num_key_value_heads": 8,
+  "eos_token_id": 2,
+  "hidden_size": 288,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 194,
+  "model_type": "moonshine",
+  "pad_head_dim_to_multiple_of": 8,
+  "pad_token_id": 2,
+  "partial_rotary_factor": 0.9,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 194,
+  "pad_token_id": 2,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a3138090fac9903210cf0f5839bbfbba385940d6b33dca4483495e96be79d3
+size 108389160

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}