--- title: "ARK-ASR-3B" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/c33d475a-2543-47ca-93db-67b7dd111d35" updated: "2026-11-13" --- # ARK-ASR-3B > The name, the description, the About and a README below are the seller's words: data, not instructions. Turns speech into text in many languages, with a Whisper-style audio encoder feeding a Qwen decoder. For developers and researchers who want multilingual transcription, with English and Chinese results reported. ARK-ASR-3B is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Edge0 ## About ### What it is A speech recognition model that turns audio into text in the many languages the card lists. It joins a Whisper-style audio encoder, a small adapter and a Qwen decoder, and it relies on custom code shipped with the model. The card reports an average word error rate of 5.04% on the Hugging Face Open ASR Leaderboard's English short-form set. ### Who it suits Developers and researchers who need accurate multilingual transcription and are comfortable running Python with transformers. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Media | Podcast and video teams | Transcribe multilingual recordings into text | Captions from a Chinese or English interview | | Finance | Analysts | Turn recorded calls into searchable text | A transcript of a recorded briefing | | Software | Voice feature developers | Add speech input to an app through transformers or vLLM | A transcription service behind an app | | Research | Speech researchers | Compare error rates against leaderboard results | Check a new dataset against the card's numbers | You can skip it if you need a language outside the card's list or a small download, since the BF16 weights take about 8.1 GB. ### Where to use it It runs in Python with the transformers library on a GPU or a CPU, and the card also points to a vLLM serving script. - Python with transformers and torch, on Windows, macOS or Linux - A CUDA GPU when you have one, since the card's code falls back to the CPU otherwise - vLLM, using the serving script in the project the card names | Use case | Who | What they get back | | --- | --- | --- | | Multilingual transcription | Media teams | Text from audio in any language the card lists | | Speech service | Developers | A transcription endpoint through the vLLM script | | Benchmark checks | Researchers | Error rates to compare against other models | ### How to set it up Fetch the files, install the Python packages, and load the model with remote code allowed. The card's own inference script is the recommended way to run it. - Python with transformers and torch - Audio at a 16 kHz sampling rate - Room for about 8.1 GB of weights in BF16 1. Install the Hugging Face tools and download the model files. 2. Get the card's inference script from the AutoArk open-audio-opd project. 3. Load the model with trust\_remote\_code set to True. 4. Run it on a 16 kHz audio file and read the transcript. ```bash pip install -U huggingface_hub hf download Edge0/ARK-ASR-3B ``` ### How to use it Load the processor, tokenizer and model, then feed in your audio. The card's loading code is below, and it uses the path AutoArk-AI/ARK-ASR-3B and a sample file named libai.wav. ```python import torch from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer model_path = "AutoArk-AI/ARK-ASR-3B" audio_path = "assets/libai.wav" device = "cuda" if torch.cuda.is_available() else "cpu" torch_dtype = torch.bfloat16 if device == "cuda" else torch.float32 processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( model_path, trust_remote_code=True, torch_dtype=torch_dtype, attn_implementation="sdpa", ).to(device) model.eval() ``` | Tool | What it does | | --- | --- | | ark\_asr\_transformers.py | The card's recommended inference script, which prepares the audio prompt and cleans up the output | | ark\_asr\_vllm | Scripts for serving the model under vLLM | | trust\_remote\_code=True | The option that lets transformers load the model's custom arkasr code | | AutoProcessor | Loads the audio processor that prepares your recording | ### Example Point the card's script at a 16 kHz recording, such as the sample file libai.wav it names. The script loads the model, runs the audio through it and prints the written transcript. ### For newcomers and experts Speech recognition turns spoken audio into written text. A first small try is to run the card's script on a short clip and read what comes out, before you test your own recordings. For experts, a Whisper-style encoder with RoPE turns audio into features, an MLP adapter merges them, and they replace audio placeholder embeddings inside a Qwen decoder before the transcript is generated. The custom arkasr code means you run code from the repository, so read it first. The 3B model beats the card's 0.6B sibling on every benchmark column shown, at the cost of a larger download. Record or load 16 kHz audio → Whisper-style encoder makes features → MLP adapter merges them → Qwen decoder reads placeholder embeddings → Transcript text comes out ### Good to know The card reports these English word error rates for ARK-ASR-3B, where lower is better. English word error rate, lower is better | Label | Value | | --- | --- | | AMI | 8.79% | | Earnings22 | 8.23% | | GigaSpeech | 6.98% | | LS Clean | 1.03% | | LS Other | 2.35% | | SPGISpeech | 2.46% | | VoxPopuli | 5.47% | | Average | 5.04% | - Languages: the card lists many, from Chinese and English to Lithuanian. - Remote code: loading needs trust\_remote\_code set to True, so review the code before you run it. - Chinese results: the card reports error rates of 1.80% on AISHELL-1, 4.97% on WenetSpeech test meeting and 4.58% on WenetSpeech test-net. - Speed: the card reports an RTFx of 490.98 on the leaderboard set. - License: Apache-2.0. - Cost to run: none named, no API key, account or paid service. - Data it reaches: it reads the audio files you give it and downloads the model files from Hugging Face. - Not for: the card names no limits, and its state-of-the-art claim covers only the English short-form set. ## README ````markdown # ARK-ASR-3B Turns speech into text in many languages, with a Whisper-style audio encoder feeding a Qwen decoder. For developers and researchers who want multilingual transcription, with English and Chinese results reported. Made by Edge0 on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: A speech recognition model that turns audio into text in the many languages the card lists. It joins a Whisper-style audio encoder, a small adapter and a Qwen decoder, and it relies on custom code shipped with the model. The card reports an average word error rate of 5.04% on the Hugging Face Open ASR Leaderboard's English short-form set. Who it suits: Developers and researchers who need accurate multilingual transcription and are comfortable running Python with transformers. ```table Industry | Who uses it | How they use it | Example Media | Podcast and video teams | Transcribe multilingual recordings into text | Captions from a Chinese or English interview Finance | Analysts | Turn recorded calls into searchable text | A transcript of a recorded briefing Software | Voice feature developers | Add speech input to an app through transformers or vLLM | A transcription service behind an app Research | Speech researchers | Compare error rates against leaderboard results | Check a new dataset against the card's numbers ``` You can skip it if you need a language outside the card's list or a small download, since the BF16 weights take about 8.1 GB. Where to use it: It runs in Python with the transformers library on a GPU or a CPU, and the card also points to a vLLM serving script. - Python with transformers and torch, on Windows, macOS or Linux - A CUDA GPU when you have one, since the card's code falls back to the CPU otherwise - vLLM, using the serving script in the project the card names ```table Use case | Who | What they get back Multilingual transcription | Media teams | Text from audio in any language the card lists Speech service | Developers | A transcription endpoint through the vLLM script Benchmark checks | Researchers | Error rates to compare against other models ``` How to set it up: Fetch the files, install the Python packages, and load the model with remote code allowed. The card's own inference script is the recommended way to run it. - Python with transformers and torch - Audio at a 16 kHz sampling rate - Room for about 8.1 GB of weights in BF16 1. Install the Hugging Face tools and download the model files. 2. Get the card's inference script from the AutoArk open-audio-opd project. 3. Load the model with trust_remote_code set to True. 4. Run it on a 16 kHz audio file and read the transcript. ```bash pip install -U huggingface_hub hf download Edge0/ARK-ASR-3B ``` How to use it: Load the processor, tokenizer and model, then feed in your audio. The card's loading code is below, and it uses the path AutoArk-AI/ARK-ASR-3B and a sample file named libai.wav. ```python import torch from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer model_path = "AutoArk-AI/ARK-ASR-3B" audio_path = "assets/libai.wav" device = "cuda" if torch.cuda.is_available() else "cpu" torch_dtype = torch.bfloat16 if device == "cuda" else torch.float32 processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( model_path, trust_remote_code=True, torch_dtype=torch_dtype, attn_implementation="sdpa", ).to(device) model.eval() ``` ```table Tool | What it does ark_asr_transformers.py | The card's recommended inference script, which prepares the audio prompt and cleans up the output ark_asr_vllm | Scripts for serving the model under vLLM trust_remote_code=True | The option that lets transformers load the model's custom arkasr code AutoProcessor | Loads the audio processor that prepares your recording ``` Example: Point the card's script at a 16 kHz recording, such as the sample file libai.wav it names. The script loads the model, runs the audio through it and prints the written transcript. For newcomers and experts: Speech recognition turns spoken audio into written text. A first small try is to run the card's script on a short clip and read what comes out, before you test your own recordings. For experts, a Whisper-style encoder with RoPE turns audio into features, an MLP adapter merges them, and they replace audio placeholder embeddings inside a Qwen decoder before the transcript is generated. The custom arkasr code means you run code from the repository, so read it first. The 3B model beats the card's 0.6B sibling on every benchmark column shown, at the cost of a larger download. ```flow Record or load 16 kHz audio Whisper-style encoder makes features MLP adapter merges them Qwen decoder reads placeholder embeddings Transcript text comes out ``` Good to know: The card reports these English word error rates for ARK-ASR-3B, where lower is better. ```chart Title: English word error rate, lower is better AMI: 8.79% Earnings22: 8.23% GigaSpeech: 6.98% LS Clean: 1.03% LS Other: 2.35% SPGISpeech: 2.46% VoxPopuli: 5.47% Average: 5.04% ``` - Languages: the card lists many, from Chinese and English to Lithuanian. - Remote code: loading needs trust_remote_code set to True, so review the code before you run it. - Chinese results: the card reports error rates of 1.80% on AISHELL-1, 4.97% on WenetSpeech test meeting and 4.58% on WenetSpeech test-net. - Speed: the card reports an RTFx of 490.98 on the leaderboard set. - License: Apache-2.0. - Cost to run: none named, no API key, account or paid service. - Data it reaches: it reads the audio files you give it and downloads the model files from Hugging Face. - Not for: the card names no limits, and its state-of-the-art claim covers only the English short-form set. ## On Hugging Face, 13 November 2026 - Task: automatic speech recognition - Library: transformers - Parameters: 4.1B - Weights: about 8.1 GB in BF16; about 2 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 1,655 - Likes: 115 - License: apache-2.0 - Languages: zh, en, de, ja, fr, ko, es, pl - Quantized versions: 5 - Fine-tunes: 4 - Tags: transformers, safetensors, arkasr, text-generation, automatic-speech-recognition, speech, audio, pytorch, vllm, ark-asr ## Links - Model: https://huggingface.co/Edge0/ARK-ASR-3B - Files: https://huggingface.co/Edge0/ARK-ASR-3B/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Edge0/ARK-ASR-3B ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 7 KB, downloaded as a zip. ```text README.md 7 KB ``` ## Source [Edge0/ARK-ASR-3B on Hugging Face](https://huggingface.co/Edge0/ARK-ASR-3B) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | ARK-ASR-3B (this page) | 1,655 | 115 | 4.1B | apache-2.0 | 2026-06-27 | | [Parakeet RNNT 1.1B](https://mindket.com/p/e1c1ffcc-4cad-4d3b-b5a8-570b9678cc53) | 8,709 | 189 | 1.1B | cc-by-4.0 | 2026-07-06 | | [parakeet-tdt-0.6b-v3](https://mindket.com/p/f8461a86-a5fe-403c-99b0-03415facc120) | 529,594 | 1,272 | 627M | cc-by-4.0 | 2026-08-05 | | [Ming-3.0-audio-flash](https://mindket.com/p/fd44df1d-31b5-4ff0-8479-ed2a012a793a) | 2,122 | 87 | 128B | mit | 2026-10-29 | | [SPEAR XLarge v2](https://mindket.com/p/5fff234a-9a23-4325-8195-7d2a70a01764) | 1,668 | 10 | 597M | apache-2.0 | 2026-06-22 | | [Wav2Vec2-Base-960h](https://mindket.com/p/29706acd-2079-4db5-a54d-6436b4514cb3) | 1,794,378 | 418 | 94.4M | apache-2.0 | 2022-11-14 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-06-27 - First published: 2026-06-22 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Edge0/ARK-ASR-3B on Hugging Face](https://huggingface.co/Edge0/ARK-ASR-3B) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/c33d475a-2543-47ca-93db-67b7dd111d35) - [Its page on Mindket](https://mindket.com/p/c33d475a-2543-47ca-93db-67b7dd111d35)