OpenHubAI
Community model & dataset hub

Stop renting intelligence.

Run models on hardware you control. No API key, no per-token bill, no cloud dependency. Structured reviews and enforced documentation are how you tell which ones are actually worth running.

Start with the task
Vision-languageText generationOtherEmbeddingsSpeech recognitionTime seriesFill-maskImage classification

13 models · Speech recognition · apache-2.0

Highest ratedMost reviewedNewest
Cards List
Rank by dimensionAccuracyFine-tuneDocsSpeed
jonatasgrosman/wav2vec2-large-xlsr-53-japanese

Documentation incomplete.

Speech recognitionapache-2.0
—
jonatasgrosman/wav2vec2-large-xlsr-53-portuguese

Documentation incomplete.

Speech recognitionapache-2.0
—
openai/whisper-large-v3

Documentation incomplete.

Speech recognitionapache-2.0
—
jonatasgrosman/wav2vec2-large-xlsr-53-russian

Documentation incomplete.

Speech recognitionapache-2.0
—
jonatasgrosman/wav2vec2-large-xlsr-53-polish

Documentation incomplete.

Speech recognitionapache-2.0
—
jonatasgrosman/wav2vec2-large-xlsr-53-dutch

Documentation incomplete.

Speech recognitionapache-2.0
—
indonesian-nlp/wav2vec2-indonesian-javanese-sundanese

Documentation incomplete.

Speech recognitionapache-2.0
—
openai/whisper-small

Documentation incomplete.

Speech recognitionapache-2.0
—
jonatasgrosman/wav2vec2-large-xlsr-53-greek

Documentation incomplete.

Speech recognitionapache-2.0
—
Qwen/Qwen3-ASR-1.7B

Documentation incomplete.

Speech recognitionapache-2.0
—
jonatasgrosman/wav2vec2-large-xlsr-53-hungarian

Documentation incomplete.

Speech recognitionapache-2.0
—
mistralai/Voxtral-Mini-4B-Realtime-2602

Documentation incomplete.

Speech recognitionapache-2.0
—
jonatasgrosman/wav2vec2-large-xlsr-53-arabic

Documentation incomplete.

Speech recognitionapache-2.0
—