Haas-ja-v1.0

Haas-ja-v1.0 is a Japanese speech recognition model built to be both fast and accurate. It is based on NVIDIA's Parakeet-TDT architecture: a FastConformer encoder and a Token-and-Duration Transducer (TDT) decoder, here with a prediction network that uses Kimi Delta Attention (KDA). The name is an acronym of Hear Anything At Speed and a nod to Helmut Haas, the acoustician behind the Haas (precedence) effect used in stereo sound and other audio technology.

At release, Haas-ja-v1.0 sits on the Pareto frontier of speed and accuracy on a benchmark built from five public Japanese datasets, and is the most accurate of the open models we evaluated (CER strict 6.12%). Its accuracy is competitive with major commercial speech-to-text APIs at a small fraction of their cost.

The blog post covers the development in more detail, including a preliminary experiment comparing prediction networks, the evaluation design and the full results.

Model details

Haas-ja-v1.0 follows Parakeet-TDT: a FastConformer encoder and a TDT decoder. TDT extends RNN-T by also predicting how long each token lasts, so decoding can jump ahead several encoder frames at a time instead of visiting every frame. Haas-ja-v1.0 replaces the LSTM in Parakeet-TDT's prediction network with Kimi Delta Attention (KDA), which improves accuracy at almost the same inference speed.

The full architecture configuration is in config.yaml.

How to use

Requirements: Linux with an NVIDIA GPU, Python 3.11+ and NeMo 2.7. The prediction network runs on kernels from flash-linear-attention, which needs Triton and CUDA, so CPU and macOS are not supported.

Try it with the repository

Clone the GitHub repository and install it with uv, which installs the exact dependency versions we tested:

git clone https://github.com/third-intelligence/Haas-ASR.git
cd Haas-ASR
uv sync
uv run python examples/quickstart.py --model third-intelligence/Haas-ja-v1.0 example.wav

Use it in your own project

Install the inference package into your environment:

pip install "haas-asr @ git+https://github.com/third-intelligence/Haas-ASR.git"

Then transcribe:

import haas_asr

model = haas_asr.load_model("third-intelligence/Haas-ja-v1.0")
audio = haas_asr.load_audio("example.wav")
output = model.transcribe([audio])
print(output[0].text)

load_model returns a regular NeMo ASRModel and runs it in bfloat16 on a GPU, the precision used for the evaluation below. haas_asr.load_audio reads a WAV, FLAC, MP3 or OGG file, averages stereo to mono and resamples it to 16 kHz, the model's input.

For recordings longer than 30 seconds, use transcribe_longform. It splits the audio at quiet points (detected by volume) and transcribes the pieces in batches:

audio = haas_asr.load_audio("example.flac")
text = haas_asr.transcribe_longform(model, audio, batch_size=64)

Custom vocabulary

Names and terms the model rarely heard in training can be listed, so that it recognizes them more often and writes them as you want:

vocabulary = haas_asr.Vocabulary(
    {"Haas": ["ハース"], "Third Intelligence": ["サードインテリジェンス"]}
)
texts = haas_asr.transcribe(model, [audio], vocabulary=vocabulary)  # short clips
text = haas_asr.transcribe_longform(model, audio, vocabulary=vocabulary)

Each word maps its written form to its readings, the ways Haas would write it (usually in kana; several, or none if Haas already writes it as listed). The readings are boosted while decoding with NeMo's GPU phrase boosting, and replaced by the written form wherever found. Boosting can also change text where no listed word was said, so audio without speech is not boosted, and each audio is also decoded without the words: a change is kept only where it includes a whole listed word. Both decodes share one encoder pass, so a vocabulary costs about 1.3 times the time. See the repository for details.

Speaker labels

Combined with NVIDIA's speaker diarization model Nemotron-3-Diarization, Haas produces transcripts with speaker labels. The repository has a runnable example.

Training data

The model was trained on about 46,000 hours of audio from public corpora (ReazonSpeech, Common Voice 26.0 and YODAS) and internal data. An in-house filtering pipeline removed low-quality samples. To keep the evaluation fair, the benchmark data is kept fully separate: none of it, including held-out portions, was used for training.

Evaluation

Benchmark Dataset

The benchmark, asr-ja-bench v1.1, combines five public datasets chosen to cover a range of speaking styles and domains (18,318 utterances, 23.38 hours). We checked samples by hand and corrected or removed those unsuitable for evaluation, such as silent audio or transcripts that don't match the audio. The per-sample metadata (source IDs, corrections and removals) is published as asr-ja-bench, with a script that rebuilds the benchmark from the original datasets.

The datasets are summarized below.

Metrics

The same Japanese word can be written in several ways (kanji or Arabic numerals, different okurigana, kanji or kana), so references and hypotheses are normalized with the jacer library before the character error rate (CER) is computed. Three CER variants show what kind of error was made:

• CER strict counts writing a word in kanji where the reference uses kana, or the other way round, as an error. This is the primary metric.
• CER flex ignores the choice between kanji and kana, but still counts homophone errors.
• CER kana compares readings, so it only measures whether the sounds were heard correctly.

CER is micro-averaged within each dataset, and the overall score weights each dataset by its audio duration. examples/evaluate_asr_ja_bench.py in the repository reproduces the Haas-ja-v1.0 results.

Results

In each cell, the top value is CER strict and the bottom values are CER flex / kana (%, lower is better). Models are sorted by weighted CER strict.

Haas-ja-v1.0 reaches a weighted CER strict of 6.12%, the best of the open models evaluated. It is competitive with commercial APIs: on par with GPT-Transcribe (6.07%), while MAI-Transcribe 2, Scribe v2 and Gemini 3.1 Pro remain more accurate.

Among open models, Haas-ja-v1.0 is on the Pareto frontier of speed and accuracy. It runs at almost the same speed as Parakeet (RTFx 3,236 vs. 3,407) while cutting CER strict by about 1.1 points, and is about 15–17 times faster than Nemotron 3.5 Transcribe and Whisper large-v3, the next most accurate open models.

RTFx (seconds of audio transcribed per second) was measured for every open model on one NVIDIA H200 at batch size 512 (Whisper large-v3 at 256, to fit in memory), and depends on the hardware and batch size. Nemotron 3.5 Transcribe ran on a vLLM server with the settings recommended in NVIDIA's model card. For commercial APIs, the Speed Factor is the audio duration divided by the total response time through OpenRouter. It includes the network and each provider's own processing, so it is a reference rather than a like-for-like comparison.

In cost terms, Haas-ja-v1.0 transcribes an hour of audio for about $0.003–0.004: roughly 1/70–1/100 of GPT-Transcribe (about $0.30), which has similar accuracy, and about 1/30 of MAI-Transcribe 2 and Scribe v2 (about $0.11), two of the cheapest commercial APIs.

Open-model costs are estimated from the measured H200 time and on-demand H200 prices in Japan regions (AWS p5en.48xlarge in Tokyo, Azure ND96isr H200 v5 in Japan East), assuming the GPU is always busy; they exclude the operating costs and margins of running a service. API costs are what OpenRouter billed during the evaluation.

Limitations

• Streaming. The model is trained for offline transcription, where it sees the whole utterance at once. It can still produce live captions by re-transcribing the current phrase as audio arrives (see the demo in the repository), but low-latency streaming may need further tuning.
• Non-verbal information. On its own, the model transcribes what is said, not who says it or how: speaker identity, emotion and other non-verbal information are not recognized. Speaker labels are possible by combining it with a diarization model (see How to use).
• Output format. The output style cannot be controlled, for example whether fillers are included. The model tends to omit fillers, and its choices of kanji, kana and numerals follow its training data. The custom vocabulary can fix the spelling of individual words, but not the style as a whole.

Acknowledgements

Haas-ja-v1.0 stands on the work of many people, and we are grateful to all of them. It builds on NVIDIA NeMo and the Parakeet-TDT architecture: a FastConformer encoder with a Token-and-Duration Transducer decoder. Its prediction network uses Kimi Delta Attention from Kimi Linear, run on the kernels of flash-linear-attention, and it was trained with Lhotse. The speaker-label example uses NVIDIA's Nemotron-3-Diarization (OpenMDW-1.1). We thank the authors of these projects for making them openly available.

We also thank the creators of ReazonSpeech, Common Voice and YODAS, whose openly released speech made training possible, and the authors of JSUT, JVNV, TEDxJP-10K, FLEURS and SpeechBSD, whose test sets make up our benchmark.

License

The model weights and the inference code are released under the Apache 2.0 License. Third-party components retain their respective licenses.