Speech Recognition Models
Models that transcribe spoken audio into text (ASR / speech-to-text).
- Top-10 combined DL 30D
- 67M
- Tasks directory position
- See all tasks
- Growth history
- Available
- Last refresh
- Sep 22, 2026
Trending now
| # | Model | Task | DL 30D | 7D | Likes | Params |
|---|---|---|---|---|---|---|
| 1 | whistleCactus-Compute | Speech Recognition | 2,249 | — | ||
| 2 | Phonon-2FermionResearch | Speech Recognition | 3,750 | — | ||
| 3 | speaker-diarization-community-1pyannote | Speech Recognition | 5.6M | 5.9%(up) | ||
| 4 | parakeet-reduxmoondream | Speech Recognition | 12.7K | — | ||
| 5 | speaker-diarization-3.1pyannote | Speech Recognition | 7.2M | 0.5%(up) | ||
| 6 | Audio8-ASR-InfiniteEdge0 | Speech Recognition | 40.5K | — | ||
| 7 | whisper-large-v3openai | Speech Recognition | 4M | 0.6%(up) | ||
| 8 | Confucius4-R2T2netease-youdao | Speech Recognition | 19.6K | — | ||
| 9 | nemotron-3.5-asr-streaming-0.6bnvidia | Speech Recognition | 1.3M | 9.5%(up) | ||
| 10 | parakeet-ultramoondream | Speech Recognition | 10.4K | — |
Most downloaded
| Model | Task | DL 30D | 7D | Likes | Params |
|---|---|---|---|---|---|
| wav2vec2-large-xlsr-53-japanesejonatasgrosman | Speech Recognition | 16.2M | 4.1%(up) | ||
| whisperkit-coremlargmaxinc | Speech Recognition | 10.8M | 3.8%(up) | ||
| speaker-diarization-3.1pyannote | Speech Recognition | 7.2M | 0.5%(up) | ||
| whisper-large-v3-turboopenai | Speech Recognition | 6.3M | 1.4%(up) | ||
| wav2vec2-large-xlsr-53-portuguesejonatasgrosman | Speech Recognition | 5.6M | 0.9%(up) | ||
| speaker-diarization-community-1pyannote | Speech Recognition | 5.6M | 5.9%(up) | ||
| wav2vec2-large-xlsr-53-russianjonatasgrosman | Speech Recognition | 4.2M | 0.8%(up) | ||
| whisper-large-v3openai | Speech Recognition | 4M | 0.6%(up) | ||
| faster-whisper-smallSystran | Speech Recognition | 3.9M | 5.4%(up) | ||
| whisper-smallopenai | Speech Recognition | 3.2M | 0.5%(up) |
Fastest growing
Downloads gained over the last seven tracked days.
| Model | Task | DL 30D | 7D7D gained | Likes | Params |
|---|---|---|---|---|---|
| wav2vec2-large-xlsr-53-japanesejonatasgrosman | Speech Recognition | 16.2M | +4M | ||
| whisperkit-coremlargmaxinc | Speech Recognition | 10.8M | +2.7M | ||
| speaker-diarization-3.1pyannote | Speech Recognition | 7.2M | +1.8M | ||
| speaker-diarization-community-1pyannote | Speech Recognition | 5.6M | +1.7M | ||
| whisper-large-v3-turboopenai | Speech Recognition | 6.3M | +1.7M | ||
| wav2vec2-large-xlsr-53-portuguesejonatasgrosman | Speech Recognition | 5.6M | +1.5M | ||
| wav2vec2-large-xlsr-53-russianjonatasgrosman | Speech Recognition | 4.2M | +1.1M | ||
| faster-whisper-smallSystran | Speech Recognition | 3.9M | +886.2K | ||
| whisper-large-v3openai | Speech Recognition | 4M | +876.1K | ||
| wav2vec2-large-xlsr-53-polishjonatasgrosman | Speech Recognition | 2.5M | +855.4K |
New & notable
Published within the last 90 days with meaningful traction.
| Model | Task | DL 30D | 7D7D gained | Likes | Params | Published |
|---|---|---|---|---|---|---|
| VibeVoice-ASR-Streaming-7B-GGUFaudio-cpp | Speech Recognition | 80.5K | +25.7K | Sep 9, 2026 | ||
| VibeVoice-ASR-BitNetmicrosoft | Speech Recognition | 69K | +19.5K | Jul 24, 2026 | ||
| Fun-ASR-Nano-2512-GGUFFunAudioLLM | Speech Recognition | 65.9K | +19.2K | Jul 29, 2026 | ||
| GigaAM-Multilingualai-sage | Speech Recognition | 61.1K | +10.7K | Jul 14, 2026 | ||
| granite-speech-5.0-470m-turboctcibm-granite | Speech Recognition | 58K | +15.8K | Aug 4, 2026 | ||
| typhoon-asr-qwen-0.6b-ctxtyphoon-ai | Speech Recognition | 43.9K | +87 | Sep 3, 2026 | ||
| Audio8-ASR-InfiniteEdge0 | Speech Recognition | 40.5K | — | Sep 21, 2026 | ||
| orukeetoruk | Speech Recognition | 39.1K | +11.9K | Sep 9, 2026 | ||
| SraVaani-0.5-liveARTPARK-IISc | Speech Recognition | 38.6K | +95 | Jul 16, 2026 | ||
| VibeVoice-ASR-Streaming-1.5B-GGUFchristopherthompson81 | Speech Recognition | 34.8K | — | Sep 19, 2026 |