| --- |
| license: other |
| license_name: desert-ant-labs-source-available-1.0 |
| license_link: https://license.desertant.com/1.0 |
| language: |
| - bg |
| - cs |
| - da |
| - de |
| - el |
| - en |
| - es |
| - et |
| - fi |
| - fr |
| - hr |
| - hu |
| - it |
| - lt |
| - lv |
| - mt |
| - nl |
| - pl |
| - pt |
| - ro |
| - ru |
| - sk |
| - sl |
| - sv |
| - uk |
| tags: |
| - speech |
| - speech-recognition |
| - transcription |
| - word-timestamps |
| - on-device |
| - core-ml |
| - apple-neural-engine |
| - multilingual |
| pipeline_tag: automatic-speech-recognition |
| --- |
| |
| <!-- card-header:start (generated from manifest.json, edit below this block) --> |
| # Voz |
|
|
| Transcribe 10 minutes in 2 seconds. |
|
|
| On-device speech recognition: transcripts with word-level timestamps, 25 languages. |
|
|
| - **SDKs, install and examples:** https://github.com/Desert-Ant-Labs/desert-ant-core/blob/main/docs/models/voz.md |
|
|
| <!-- card-header:end --> |
|
|
| Transcribes speech to text with word-level timestamps, in 25 languages, with the |
| whole graph resident on the Neural Engine. Half an hour of audio takes about |
| seven seconds on an M3 Ultra, and peak memory does not grow with the length of |
| the recording. |
|
|
| > `"We made the bet to build for iOS"` - each word with a start and an end, so a |
| > range is enough to cut on. |
|
|
| ## Try it |
|
|
| Ships as an Apple SwiftPM package: **[Desert-Ant-Labs/desert-ant-core](https://github.com/Desert-Ant-Labs/desert-ant-core)**. |
|
|
| - **iOS / iPadOS / Mac Catalyst / macOS / tvOS / visionOS:** the Swift SDK (Swift |
| Package Manager). The models below are downloaded on demand and cached, so |
| nothing is bundled into your app. |
| - Apple-only. The SDK drives Core ML directly to keep the graph on the Neural |
| Engine, which has no equivalent on the other backends. |
|
|
| ```swift |
| let voz = try await Voz() |
| let result = try await voz.transcribe(url) |
| result.text // "We made the bet to build for iOS..." |
| result.words.first?.start // 0.32 |
| result.words.first?.end // 0.58 |
| ``` |
|
|
| ## Files |
|
|
| | File | What it is | |
| |---|---| |
| | `encoder.mlmodelc` | Acoustic encoder | |
| | `mel.mlmodelc` | Audio frontend | |
| | `decoder.mlmodelc` | Decoder | |
| | `meta.json` | Geometry the runtime reads instead of hardcoding | |
| | `vocab.json` | SentencePiece vocabulary | |
| | `embedding.f16` | Token embedding table | |
|
|
| Artifact names describe roles rather than the network behind them, so replacing |
| the recogniser is a new upload rather than an SDK change. |
|
|
| The models are shipped **compiled** (`.mlmodelc`). Keep them that way: an |
| `.mlpackage` is recompiled on every launch and loads far more slowly. |
|
|
| ## Architecture |
|
|
| A three-stage Core ML cascade over a log-mel spectrogram, dispatched from Swift: |
|
|
| - **Frontend**: a log-mel spectrogram computed inside Core ML, normalized over the frames |
| that hold audio rather than the whole padded window. |
| - **Encoder**: a conformer-style acoustic encoder over a fixed 15 s window, producing one |
| frame every 80 ms. |
| - **Decoder**: a transducer that emits a token and a duration at each step, run with sixteen |
| independent windows batched into the lanes of a single dispatch. |
|
|
| Longer audio is cut into consecutive windows at pauses, transcribed independently, and |
| joined on the longest run of words two neighbouring windows agree on. Every stage runs on |
| the Neural Engine with no CPU or GPU fallback. |
|
|
| ## Inputs and outputs |
|
|
| - **Input:** mono audio at any sample rate; the SDK resamples and downmixes. |
| - **Output:** the transcript, plus every word with a start and an end in seconds. |
|
|
| ## Accuracy |
|
|
| Ten minutes of audio on an M3 Ultra, release build, warm: |
|
|
| | | | |
| |---|---| |
| | Speed | **2.1 s for 611 s of audio (~290x real time)** on long files; 50-62x transcribing single short utterances, where every clip pays for a full 15 s window | |
| | Word error rate | **7.40%** averaged over six Open ASR Leaderboard sets, against 7.00% for Whisper large-v3-turbo | |
| | Long-form word error rate | **2.83%** on half an hour of narration scored against the book, against 2.72% for Whisper large-v3-turbo on the same span | |
| | Word timestamps | starts 83 ms, ends 95 ms mean absolute error against a forced aligner | |
| | Neural Engine residency | 100%, with no CPU or GPU fallback | |
| | Size on disk | 467 MB | |
| | Load | ~0.2 s warm; ~20 s once per install while Core ML specializes | |
|
|
| ### English, on the Open ASR Leaderboard |
|
|
| Scored on the [Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) |
| datasets with its own text normalizer. Whisper's figures are the leaderboard's, |
| on the same dataset configurations. |
|
|
| | dataset | Voz | Whisper large-v3-turbo | |
| |---|---:|---:| |
| | LibriSpeech test-clean | 2.19% | 2.13% | |
| | LibriSpeech test-other | 3.86% | 3.70% | |
| | GigaSpeech | 9.70% | 8.47% | |
| | SPGISpeech | 3.86% | 2.79% | |
| | Earnings-22 | 12.97% | 11.07% | |
| | AMI | 11.84% | **13.87%** | |
| | **average** | **7.40%** | **7.00%** | |
|
|
| Close overall, two points better on meetings, behind on prepared and read |
| speech. It gets there in 467 MB entirely on the Neural Engine, against 1.6 GB |
| for Whisper large-v3-turbo. |
|
|
| **Expect the conversational figures, not the LibriSpeech one.** Read speech in a |
| clean recording scores around 2%; meetings, earnings calls and podcast audio |
| score 10-13%, and most real material is nearer the second group. Roughly one word |
| in ten wanting a look is the honest expectation for a podcast. |
|
|
| VoxPopuli and TEDLIUM are omitted: the leaderboard's scripts name a 628-utterance |
| shard of the former, which is not the audio its published figure measures, and |
| the latter's config carries no rows. |
|
|
| ### Word timestamps |
|
|
| Every word carries a start and an end, scored against [torchaudio's MMS_FA |
| forced aligner](https://pytorch.org/audio/stable/generated/torchaudio.pipelines.MMS_FA.html): |
|
|
| | | words | start | end | ends within 80 ms | within 200 ms | |
| |---|---:|---:|---:|---:|---:| |
| | English, LibriSpeech | 6295 | 83 ms | 95 ms | 60% | 90% | |
| | German, FLEURS | 939 | 80 ms | 92 ms | 62% | 92% | |
|
|
| Ends are the harder of the two. The recogniser reports how far to skip after |
| each token rather than where a word stops, which overshoots into the pause that |
| follows it, so ends are trimmed back using the audio. Forced alignment is itself |
| approximate at the tens of milliseconds level, so treat these as agreement with a |
| good aligner rather than absolute truth. Much of the residual is the 80 ms frame |
| resolution, which is the floor for any word time this export produces. |
|
|
| ### Every supported language, on long audio |
|
|
| Ten minutes per language, built by concatenating [FLEURS](https://huggingface.co/datasets/google/fleurs) |
| test utterances so that each file crosses about forty analysis boundaries. A |
| single FLEURS utterance is shorter than one window and so measures nothing about |
| how consecutive windows are joined, which is most of what happens on real |
| material. 4.2 hours in total. |
|
|
| | | WER | | WER | | WER | |
| |---|---:|---|---:|---|---:| |
| | it | 3.31% | cs | 14.27% | hu | 21.26% | |
| | pt | 6.08% | sk | 15.42% | et | 21.37% | |
| | uk | 6.40% | hr | 16.92% | sv | 21.67% | |
| | ru | 6.57% | fi | 18.17% | mt | 22.01% | |
| | en | 7.36% | ro | 20.95% | da | 24.32% | |
| | de | 8.12% | | | lt | 26.89% | |
| | es | 9.01% | | | lv | 30.57% | |
| | nl | 9.84% | | | sl | 33.85% | |
| | pl | 9.99% | | | el | 39.46% | |
| | bg | 12.39% | | | | | |
| | fr | 12.78% | | | | | |
|
|
| Aggregate 16.58%, median 283x real time. Throughput varies only 12% across |
| languages, because cost follows how much audio there is rather than what is in |
| it. |
|
|
| Read the spread before choosing a language. The nine best are usable as-is; the |
| tail above 20% will cost more to correct than to retype for many uses, and |
| reflects where the underlying recogniser is already known to be weak rather than |
| anything specific to this export. This is read speech in clean recordings, so |
| treat it as a ranking rather than as a number to expect on your own audio. |
|
|
| ## Languages |
|
|
| Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, |
| Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, |
| Slovak, Slovenian, Spanish, Swedish, and Ukrainian. |
|
|
| Accuracy varies widely across them; see the per-language table above before choosing one. |
|
|
| ## Built on |
|
|
| - [Parakeet TDT 0.6B v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) - NVIDIA |
| (CC BY 4.0): the base recogniser, converted to Core ML and compressed for this export. |
| Weight values are otherwise unchanged. |
| - [FLEURS](https://huggingface.co/datasets/google/fleurs) (CC BY 4.0): evaluation audio for |
| the per-language table above. |
|
|
| See [`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md). FLEURS is not redistributed here. |
|
|
| <!-- card-footer:start (generated from manifest.json, edit above this block) --> |
| ## License |
|
|
| [Desert Ant Labs Source-Available License](https://license.desertant.com/1.0). Free for most |
| apps, and a commercial license is required at scale. Full terms are at the link. |
| Licensing: <licensing@desertant.com>. |
|
|
| See [`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md). |
|
|
| ## Citation |
|
|
| ```bibtex |
| @software{voz_2026, |
| title = {Voz: On-device speech recognition: transcripts with word-level timestamps, 25 languages}, |
| author = {Desert Ant Labs}, |
| year = {2026}, |
| url = {https://huggingface.co/desert-ant-labs/voz}, |
| } |
| ``` |
|
|
| --- |
|
|
| © 2026 Desert Ant Labs · <https://desertant.com> |
| <!-- card-footer:end --> |
|
|
