๐ŸŽ™๏ธ Fluid Speech Pro (GGUF)

Model architecture | Model size | Language | License

Fluid Speech Pro as GGUF for parakeet.cpp: fast speech-to-text in C++, on CPU or GPU, with no Python. English and 24 other European languages, with punctuation and capitals.

All versions

Version Best for Clean mode
NeMo + ๐Ÿค— Transformers NVIDIA GPUs and servers; the reference model Yes (NeMo)
ONNX CPUs, with onnx-asr or sherpa-onnx Yes
MLX Apple Silicon Macs, with parakeet-mlx Yes
GGUF (this one) C++ with parakeet.cpp, CPU or GPU, no Python No
Core ML Apple apps in Swift, on the Neural Engine, with FluidAudio Not yet

Description

Fluid Speech Pro is a 0.63-billion-parameter speech recognition model for fast, accurate speech-to-text, from the team behind FluidVoice. It is built on NVIDIA's Parakeet TDT 0.6B v3 and keeps its 25 European languages. It detects the language on its own, with no prompt needed.

It is the #2 open model on the Open ASR Leaderboard, with a 6.06 average word error rate. It is the most accurate open model under 1B parameters, #2 among open models on noisy speech, and it runs at about 3,700ร— real time on one GPU.

This model is ready for commercial and non-commercial use.

Key features

  • Accurate: #2 open model on the Open ASR Leaderboard (6.06 average WER)
  • Best under 1B: 10% fewer errors than the next open model under 1B parameters
  • Strong in noise: #2 open model on URGENT 2024, the leaderboard's noisy-speech set (9.83 WER)
  • Fast: about 3,700ร— real time on one GPU, so an hour of audio takes about a second
  • Punctuation and capitalization included
  • Word- and segment-level timestamps (NeMo)
  • Clean mode (optional): edited text without repeated words and filler words (NeMo, ONNX and MLX versions; not in this GGUF)
  • 25 European languages, detected automatically
  • Five versions: NeMo and ๐Ÿค— Transformers, ONNX, MLX, GGUF and Core ML
  • Permissive license: CC BY 4.0

Performance

Accuracy against size for open models on the Open ASR Leaderboard

Figure 1: Average word error rate (up is better) against model size for open models on the Open ASR Leaderboard. Fluid Speech Pro is the only top-5 open model under 1B parameters.

The most accurate open model under 1B parameters

Figure 2: The best open models at 1B parameters and under, ranked by average word error rate (lower is better).

Second among open models on noisy speech

Figure 3: Word error rate on URGENT 2024, the leaderboard's noisy-speech set (lower is better).

Quick start

hf download FluidVoice-Labs/fluid-speech-pro-gguf fluid-speech-pro-q8_0.gguf --local-dir .
parakeet-cli transcribe --model fluid-speech-pro-q8_0.gguf --input audio.wav

Get parakeet-cli by building parakeet.cpp. On a Mac, add -DPARAKEET_GGML_METAL=ON to run on the GPU. Input is a 16 kHz mono WAV.

How it differs from the main model

  • These files hold Fluid Speech Pro in the plain Parakeet TDT 0.6B v3 layout, so parakeet.cpp runs them as they are.
  • Clean mode is not available here, and the model's small extra block is left out. That block matters most for noisy speech, so noisy audio may come out a little worse.
  • Overall accuracy stays about the same: on our check below, WER 3.44 (f32) and 3.47 (q8_0), against 3.53 for the full model.
  • For clean mode and the complete model, use the NeMo, ONNX or MLX versions.

Files

File Weights Download
fluid-speech-pro-q8_0.gguf 8-bit (Q8_0) 941 MB
fluid-speech-pro-f32.gguf fp32 2.51 GB

Accuracy of this version

400 clips from 8 public test sets (AMI, Earnings-22, GigaSpeech, LibriSpeech clean and other, Monsoon, SPGISpeech, VoxPopuli). All runs decode greedily.

Run Same text as the full model WER
Full model (NeMo, reference) 400 / 400 3.53
parakeet.cpp, f32 370 / 400 3.44
parakeet.cpp, q8_0 367 / 400 3.47

WER is over the 350 clips from the 7 sets with per-clip references (Earnings-22's references are whole calls).

Good to know

  • Speed on an Apple M5 Max, one clip at a time: about 165ร— real time on the GPU (Metal build); on the CPU, about 27ร— (q8_0) and 13ร— (f32).
  • Tested with parakeet.cpp at commit 2eac2e7 (October 2026).

Use case

For developers, researchers and companies building anything that turns speech into text: dictation, meeting notes, captions and subtitles, voice assistants, call and media analytics, and transcription services.

Release date

Hugging Face, November 2026.

Model architecture

Architecture type: FastConformer-TDT

Network architecture:

  • A FastConformer encoder and a TDT (token-and-duration transducer) decoder, as in Parakeet TDT 0.6B v3
  • One small extra block between the encoder's subsampling and its first Conformer layer
  • 0.63 billion parameters

Input

  • Input type: audio, 16 kHz, mono
  • Input format: .wav, .flac and other formats your audio loader reads

Output

  • Output type: text, with punctuation and capitalization
  • Optional: word and segment timestamps (NeMo)

Model version

Fluid Speech Pro 1.0

Evaluation datasets

The Open ASR Leaderboard's public test sets: AMI (cleaned), Earnings-22 (cleaned, chunked), GigaSpeech (cleaned), SPGISpeech, URGENT 2024 (noisy speech), Voice Arena Monsoon (Indian English) and VoxPopuli (cleaned).

Results

The leaderboard numbers below are for the main NeMo model with 4-beam search. This GGUF version leaves out the small extra block and clean mode; see Accuracy of this version for how it compares.

Open ASR Leaderboard

Open models on the Open ASR Leaderboard: average word error rate over its seven public and two private test sets (lower is better):

Model Parameters Average WER
Musci-ASR 2B 5.70
Fluid Speech Pro 0.63B 6.06
NVIDIA Nemotron 3.5 Transcribe 30B 6.13
Qwen3-ASR 1.7B 6.15
IBM Granite Speech 5.0 2B 6.68
Cohere Transcribe 2B 6.72
NVIDIA Parakeet TDT 0.6B v2 0.6B 6.93
NVIDIA Parakeet TDT 0.6B v3 0.6B 7.04
Fermion Research Phonon-2 0.6B 7.86

Results by test set

Word error rate (%) on the leaderboard's seven public test sets:

Model Public average AMI Earnings-22 GigaSpeech SPGISpeech URGENT 2024 Monsoon VoxPopuli
Musci-ASR 5.15 6.53 5.83 6.41 1.86 10.49 3.44 1.47
Fluid Speech Pro 5.43 7.55 5.42 7.51 2.31* 9.83 3.71 1.70
NVIDIA Nemotron 3.5 Transcribe 5.51 7.78 5.25 7.18 1.91 10.94 3.63 1.89
Qwen3-ASR 5.75 8.31 5.84 7.22 2.57 9.93 3.50 2.85
IBM Granite Speech 5.0 6.05 6.96 6.22 8.14 3.36 10.22 3.94 3.52
Cohere Transcribe 6.26 7.02 7.88 7.88 2.74 9.50 3.44 5.38
NVIDIA Parakeet TDT 0.6B v2 6.43 9.09 6.76 8.15 1.94 11.42 3.89 3.78
NVIDIA Parakeet TDT 0.6B v3 6.51 9.42 5.85 7.99 3.63 11.52 4.14 3.05
Fermion Research Phonon-2 7.23 9.32 6.96 8.35 3.70 14.90 4.91 2.46

* In clean mode, which matches SPGISpeech's edited references; the leaderboard allows one transcription mode per test set.

Other languages

Fluid Speech Pro supports 25 languages. On the Open ASR Leaderboard's multilingual track it makes 12% fewer errors than Parakeet TDT 0.6B v3, and it is better in all seven of the track's languages:

Language Parakeet TDT 0.6B v3 Fluid Speech Pro Fewer errors
German 4.12 3.76 9%
French 5.40 5.10 6%
Italian 4.73 4.16 12%
Spanish 3.71 3.38 9%
Portuguese 6.08 4.88 20%
Dutch 7.53 6.82 9%
English 7.04 6.06 14%
Average 5.52 4.88 12%

Word error rate (%) on the Open ASR Leaderboard's multilingual track, lower is better.

It also got better than Parakeet TDT 0.6B v3 in every one of the 24 languages beyond English. On FLEURS, scored the way the leaderboard scores its multilingual track, it makes nearly 20% fewer errors on average.

Better than Parakeet TDT 0.6B v3 in all 24 other languages

Figure 4: Word error rate on FLEURS for Parakeet TDT 0.6B v3 (grey) and Fluid Speech Pro (blue), lower is better.

Language Parakeet TDT 0.6B v3 Fluid Speech Pro Fewer errors
Estonian 13.28 9.51 28%
Latvian 21.76 16.39 25%
Italian 2.48 1.91 23%
Lithuanian 21.04 16.21 23%
Maltese 19.23 15.05 22%
Hungarian 13.58 10.65 22%
Slovak 9.18 7.20 22%
Finnish 11.19 8.82 21%
Czech 11.06 8.83 20%
Portuguese 4.47 3.57 20%
Slovenian 22.48 17.97 20%
Ukrainian 5.95 4.77 20%
Greek 21.16 17.10 19%
Romanian 11.38 9.28 18%
Spanish 3.22 2.66 17%
Swedish 13.39 11.10 17%
Polish 6.84 5.70 17%
German 4.18 3.52 16%
Danish 17.20 14.57 15%
Bulgarian 11.94 10.19 15%
Croatian 11.40 9.73 15%
Dutch 6.39 5.51 14%
Russian 4.92 4.35 12%
French 4.75 4.65 2%
Average of all 24 11.35 9.13 20%

Word error rate (%) on FLEURS test sets, greedy decoding. A future version will be trained on more multilingual data.

Limitations

  • Please check the model on your own audio, accents and languages before you rely on it.
  • Like every speech model, it makes more mistakes on heavy noise, overlapping speakers, strong accents it has rarely heard, and rare names and terms.
  • Clean mode edits the text. Don't use it where you need an exact record.

License

CC BY 4.0. If you use the model, please credit it as Fluid Speech Pro by FluidVoice.

Built on NVIDIA Parakeet TDT 0.6B v3 and Moondream Parakeet Ultra, both CC BY 4.0.

Citation

@misc{fluidspeechpro2026,
  title  = {Fluid Speech Pro},
  author = {{FluidVoice}},
  year   = {2026},
  url    = {https://huggingface.co/FluidVoice-Labs/fluid-speech-pro}
}

References

  1. Parakeet TDT 0.6B v3, NVIDIA
  2. Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition
  3. Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
  4. Open ASR Leaderboard, Hugging Face
Downloads last month
534
GGUF
Model size
0.6B params
Architecture
parakeet
Hardware compatibility
Log In to add your hardware

8-bit

32-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for FluidVoice-Labs/fluid-speech-pro-gguf

Quantized
(4)
this model

Papers for FluidVoice-Labs/fluid-speech-pro-gguf