Catalogue · Audio & music
236 open-weight audio & music tracked from the labs releasing them. AxForge can deploy any of these on EU-owned hardware on request — with the commercial licence arranged where one is needed.
236 models
Newest first — click any column heading to sort.
| Model | Maker | Task | Params | Variants | Licence | Released | Downloads/mo |
|---|---|---|---|---|---|---|---|
| Breeze-TTS-2NEW | BreezeBlue | Text→speech | 3.5B | 1 | Licence fee | 2026-08-25 | 2k |
| speecht5_finetuned_iamwille_ig | iamwille | Music / audio | 144M | 1 | Open | 2026-08-19 | 759 |
| granite-speech-5.0-turboctc-nc | ibm-granite | Speech→text | 473M | 1 | Licence fee | 2026-08-17 | 675 |
| audio.cpp | CaptainArni | Music / audio | — | 1 | Open | 2026-08-16 | 14k |
| minimax_music3_text_encoder | rzgar | Music / audio | — | 1 | Licence fee | 2026-08-14 | 1k |
| MiniMax-Music3 | joemattie | Music / audio | — | 1 | Licence fee | 2026-08-14 | 1k |
| MiniMax-Music3 | audio-cpp | Music / audio | — | 1 | Licence fee | 2026-08-14 | 87k |
| MiniMax-Music3 | Abiray | Music / audio | — | 1 | Open | 2026-08-14 | 9k |
| minimax-music3 | ChrisColeTech | Music / audio | — | 1 | Licence fee | 2026-08-14 | 5k |
| MiniMax-Music-3_GGUFs | realrebelai | Music / audio | — | 1 | Open | 2026-08-14 | 1k |
| Minimax-Music3 | molbal | Music / audio | — | 1 | Open | 2026-08-13 | 17k |
| MiniMax-Music3-Serve | ddalcu | Music / audio | — | 1 | Licence fee | 2026-08-13 | 1k |
| DriftSE | LIANGXU123 | Audio→audio | — | 1 | Open | 2026-08-13 | 1k |
| midashenglm-gen | mispeech | Music / audio | 2.9B | 1 | Open | 2026-08-12 | 1k |
| IndexTTS-2.5 | IndexTeam | Text→speech | — | 1 | Licence fee | 2026-08-10 | 11k |
| MiniMax-Music3 | MiniMaxAI | Music / audio | 2.4B | 1 | Licence fee | 2026-08-07 | 22k |
| granite-speech-5.0-turboctc | ibm-granite | Speech→text | 473M | 1 | Open | 2026-08-04 | 6k |
| Audio8-TTS-ONNX | Audio8 | Text→speech | — | 2 | Open | 2026-07-31 | 1k |
| Audio8-TTS | Audio8 | Text→speech | 601M | 2 | Licence fee | 2026-07-28 | 21k |
| moss-soundeffect | ilintar | Music / audio | — | 1 | Open | 2026-07-27 | 1k |
| magpie-tts.cpp | mudler | Text→speech | — | 1 | Licence fee | 2026-07-24 | 79k |
| VibeVoice-ASR-BitNet | microsoft | Speech→text | 323M | 1 | Open | 2026-07-24 | 16k |
| CrisperWhisper2.0_large | nyralabs | Speech→text | 1.5B | 1 | Licence fee | 2026-07-15 | 31k |
| audio.cpp | audio-cpp | Text→speech | — | 1 | Licence fee | 2026-07-14 | 1.4M |
| GigaAM-Multilingual | ai-sage | Speech→text | — | 1 | Open | 2026-07-14 | 117k |
| MOSS-TTS-Local-Transformer | mudler | Text→speech | — | 1 | Open | 2026-07-12 | 158k |
| Audio8-ASR | Audio8 | Speech→text | 324M | 1 | Licence fee | 2026-07-10 | 2k |
| demodokos-foundry-music | cmp-nct | Music / audio | — | 1 | Licence fee | 2026-07-06 | 4k |
| Higgs-Audio-Studio | drbaph | Text→speech | — | 1 | Licence fee | 2026-07-02 | 200k |
| stable-audio-3-medium | thepatch | Music / audio | — | 1 | Licence fee | 2026-06-29 | 2k |
| thinksound | ilintar | Music / audio | — | 1 | Licence fee | 2026-06-28 | 3k |
| MOSS-Transcribe | OpenMOSS-Team | Speech→text | 2.4B | 1 | Open | 2026-06-26 | 1k |
| Inflect-Micro | owensong | Text→speech | — | 1 | Open | 2026-06-25 | 1k |
| dasheng-audiogen | audiohacking | Music / audio | — | 1 | Open | 2026-06-23 | 1k |
| gepard-1.0 | nineninesix | Text→speech | 556M | 1 | Open | 2026-06-22 | 50k |
| Kokoro-Vietnamese | contextboxai | Text→speech | — | 1 | Open | 2026-06-19 | 42k |
| cohere-transcribe-arabic-07-2026 | CohereLabs | Speech→text | 2.1B | 1 | Open | 2026-06-18 | 54k |
| Sidon-CoreML | aufklarer | Audio→audio | — | 1 | Open | 2026-06-14 | 2k |
| nemotron-3.5-asr-streaming | handy-computer | Speech→text | — | 1 | Licence fee | 2026-06-07 | 1.9M |
| VieNeu-TTS | pnnbao-ump | Text→speech | 131M | 2 | Open | 2026-06-05 | 426k |
| higgs-audio-tts-transformers | multimodalart | Text→speech | 4.7B | 1 | Licence fee | 2026-06-05 | 44k |
| MOSS-TTS-Local-Transformer | OpenMOSS-Team | Text→speech | 4.6B | 1 | Open | 2026-06-04 | 174k |
| higgs-tts-3 | bosonai | Text→speech | 4.7B | 1 | Licence fee | 2026-06-04 | 201k |
| personaplex-rl-seamless | kyutai | Audio→audio | 8.4B | 1 | Licence fee | 2026-06-02 | 6k |
| moshika-rl-seamless | kyutai | Audio→audio | 7.7B | 1 | Licence fee | 2026-06-02 | 185 |
| magenta-realtime-2 | Music / audio | — | 1 | Open | 2026-05-28 | 7k | |
| LFM2.5-Audio-JP | LiquidAI | Audio→audio | — | 1 | Licence fee | 2026-05-27 | 2k |
| MOSS-SoundEffect | OpenMOSS-Team | Music / audio | 1.4B | 2 | Open | 2026-05-25 | 1k |
| MOSS-TTS | OpenMOSS-Team | Text→speech | 8.5B | 1 | Open | 2026-05-25 | 413k |
| stable-audio-3-medium | cocktailpeanut | Music / audio | 2.3B | 1 | Licence fee | 2026-05-21 | 1k |
| stable-audio-3-small-music | cocktailpeanut | Music / audio | 568M | 1 | Licence fee | 2026-05-21 | 2k |
| stable-audio-3-optimized | stabilityai | Music / audio | — | 1 | Licence fee | 2026-05-18 | 13k |
| stable-audio-3-small-music | stabilityai | Music / audio | 568M | 1 | Licence fee | 2026-05-17 | 13k |
| stable-audio-3-small-sfx | stabilityai | Music / audio | 568M | 1 | Licence fee | 2026-05-17 | 18k |
| stable-audio-3-medium | stabilityai | Music / audio | 2.3B | 1 | Licence fee | 2026-05-17 | 72k |
| nemotron-3.5-asr-streaming | nvidia | Speech→text | 638M | 1 | Licence fee | 2026-05-15 | 927k |
| whisper-large-ov | OpenVINO | Speech→text | — | 1 | Open | 2026-05-13 | 1k |
| Qwen3-TTS | Serveurperso | Text→speech | — | 1 | Open | 2026-05-11 | 901k |
| parakeet-unified-en | handy-computer | Speech→text | — | 1 | Open | 2026-05-10 | 1.7M |
| supertonic-3 | Supertone | Text→speech | — | 1 | Open | 2026-05-06 | 28k |
| khmer-tts | khmerttsopensource | Music / audio | 83M | 1 | Licence fee | 2026-05-01 | 1k |
| qwen3-tts-tokenizer-12hz | cstr | Audio→audio | — | 1 | Open | 2026-04-29 | 5k |
| OmniVoice | Serveurperso | Text→speech | — | 1 | Open | 2026-04-27 | 188k |
| Audar-ASR | audarai | Speech→text | 2.3B | 1 | Licence fee | 2026-04-23 | 1k |
| LocalVQE | LocalAI-io | Audio→audio | — | 1 | Open | 2026-04-17 | 4k |
| granite-speech-4.1-plus | ibm-granite | Speech→text | 2.1B | 1 | Open | 2026-04-16 | 134k |
| granite-speech-4.1 | ibm-granite | Speech→text | 2.3B | 1 | Open | 2026-04-16 | 275k |
| cohere-transcribe-03-2026 | handy-computer | Speech→text | — | 1 | Open | 2026-04-15 | 970k |
| parakeet-tdt | handy-computer | Speech→text | — | 1 | Open | 2026-04-15 | 687k |
| Real-time_RE-USE | nvidia | Audio→audio | 13M | 1 | Licence fee | 2026-04-14 | 519 |
| Ace-Step-1.5-ScragVAE | scragnog | Audio→audio | 169M | 1 | Open | 2026-04-11 | 2k |
| qwen3-asr | cstr | Speech→text | — | 1 | Open | 2026-04-11 | 8k |
| VoxCPM2 | openbmb | Text→speech | 2.3B | 1 | Open | 2026-04-03 | 330k |
| acestep-xl | ACE-Step | Music / audio | 5.0B | 2 | Open | 2026-04-02 | 4k |
| acestep-xl-sft | ACE-Step | Music / audio | 5.0B | 2 | Open | 2026-04-02 | 6k |
| Raon-Speech | KRAFTON | Audio→audio | 9.7B | 1 | Licence fee | 2026-04-01 | 1k |
| OmniVoice | k2-fsa | Text→speech | 613M | 1 | Licence fee | 2026-03-30 | 1M |
| cohere-transcribe-03-2026 | CohereLabs | Speech→text | 2.1B | 1 | Open | 2026-03-24 | 439k |
| moshika-rag-candle | kyutai | Audio→audio | 8.4B | 1 | Open | 2026-03-19 | 495 |
| moshika-rag-pytorch | kyutai | Audio→audio | 7.7B | 1 | Open | 2026-03-19 | 1k |
| RE-USE | nvidia | Audio→audio | 10M | 1 | Licence fee | 2026-03-17 | 17k |
| unipase | Xiaobin-Rong | Audio→audio | — | 1 | Open | 2026-03-16 | 2k |
| Covo-Audio | tencent | Audio→audio | 8.4B | 1 | Licence fee | 2026-03-16 | 808 |
| qwen2-audio | forkjoin-ai | Music / audio | — | 1 | Open | 2026-03-09 | 1k |
| s2-pro | fishaudio | Text→speech | 4.6B | 1 | Licence fee | 2026-03-09 | 345k |
| jhcodec | jhcodec | Audio→audio | — | 1 | Open | 2026-03-08 | 2k |
| DeepFilterNet3-CoreML | aufklarer | Audio→audio | — | 1 | Open | 2026-03-04 | 5k |
| granite-4.0-speech | ibm-granite | Speech→text | 2.3B | 1 | Open | 2026-02-27 | 40k |
| MioCodec-25Hz-44.1kHz | Aratako | Audio→audio | 132M | 1 | Open | 2026-02-14 | 181k |
| MOSS-TTS-Realtime | OpenMOSS-Team | Text→speech | 2.3B | 1 | Open | 2026-02-09 | 54k |
| MOSS-VoiceGenerator | OpenMOSS-Team | Text→speech | 2.1B | 1 | Open | 2026-02-08 | 71k |
| Qwen3-ASR | Qwen | Speech→text | 2.3B | 4 | Open | 2026-01-28 | 4.6M |
| Ace-Step1.5 | ACE-Step | Music / audio | — | 1 | Open | 2026-01-23 | 53k |
| Voxtral-Mini-Realtime-2602 | mistralai | Speech→text | 4.4B | 1 | Open | 2026-01-21 | 2.2M |
| VibeVoice-ASR | microsoft | Speech→text | 8.7B | 1 | Open | 2026-01-21 | 700k |
| Qwen3-TTS-12Hz | Qwen | Text→speech | 915M | 1 | Open | 2026-01-21 | 533k |
| Qwen3-TTS-12Hz-CustomVoice | Qwen | Text→speech | 1.9B | 2 | Open | 2026-01-21 | 2.5M |
| Qwen3-TTS-Tokenizer-12Hz | Qwen | Audio→audio | 171M | 1 | Open | 2026-01-21 | 122k |
| Qwen3-TTS-12Hz-VoiceDesign | Qwen | Text→speech | 1.9B | 1 | Open | 2026-01-21 | 285k |
| VieNeu-TTS-q4 | pnnbao-ump | Text→speech | — | 1 | Licence fee | 2026-01-08 | 69k |
| personaplex | nvidia | Audio→audio | 8.4B | 1 | Licence fee | 2025-12-31 | 131k |
| nemotron-speech-streaming-en | nvidia | Speech→text | 618M | 1 | Licence fee | 2025-12-17 | 200k |
| Fun-CosyVoice3-2512 | FunAudioLLM | Text→speech | — | 1 | Open | 2025-12-11 | 52k |
| GLM-ASR-Nano-2512 | zai-org | Speech→text | 2.3B | 1 | Open | 2025-12-09 | 82k |
| VoxCPM1.5 | openbmb | Text→speech | 802M | 1 | Open | 2025-12-05 | 21k |
| VibeVoice-Realtime | microsoft | Text→speech | 1.0B | 1 | Open | 2025-12-04 | 599k |
| GigaAM | ai-sage | Speech→text | — | 1 | Open | 2025-11-19 | 232k |
| react-native-executorch-kokoro | software-mansion | Text→speech | — | 1 | Open | 2025-11-12 | 118k |
| svara-tts | kenpath | Text→speech | 3.3B | 1 | Open | 2025-10-26 | 191k |
| diar_streaming_sortformer_4spk | nvidia | Speech→text | — | 1 | Licence fee | 2025-10-22 | 39k |
| neutts-air-q8 | neuphonic | Text→speech | — | 1 | Open | 2025-09-23 | 56k |
| neutts-air-q4 | neuphonic | Text→speech | — | 1 | Open | 2025-09-23 | 25k |
| VibeVoice | vibevoice | Text→speech | 2.7B | 1 | Open | 2025-09-04 | 72k |
| VibeVoice | microsoft | Text→speech | 2.7B | 1 | Open | 2025-08-25 | 141k |
| parakeet-tdt | nvidia | Speech→text | 627M | 2 | Open | 2025-08-04 | 744k |
| higgs-tts-2 | bosonai | Text→speech | 5.8B | 1 | Licence fee | 2025-07-01 | 541k |
| tts-en_fr | kyutai | Text→speech | — | 1 | Open | 2025-06-30 | 185k |
| canary-qwen | nvidia | Speech→text | 2.6B | 1 | Open | 2025-06-26 | 23k |
| neucodec | neuphonic | Audio→audio | 630M | 2 | Open | 2025-06-19 | 87k |
| Breeze-ASR-25 | MediaTek-Research | Speech→text | 1.5B | 1 | Open | 2025-06-06 | 27k |
| F5-TTS_RUSSIAN | Misha24-10 | Text→speech | — | 1 | Licence fee | 2025-05-19 | 53k |
| parakeet-tdt | mlx-community | Speech→text | 618M | 2 | Open | 2025-05-06 | 2.2M |
| granite-speech-3.3 | ibm-granite | Speech→text | 3.0B | 2 | Open | 2025-04-28 | 168k |
| Kimi-Audio | moonshotai | Text→speech | 9.8B | 1 | Open | 2025-04-25 | 29k |
| chatterbox | ResembleAI | Text→speech | — | 1 | Open | 2025-04-24 | 1.8M |
| Dia | nari-labs | Text→speech | 1.6B | 1 | Open | 2025-04-20 | 31k |
| speaker-diarization-community-1 | pyannote | Speech→text | — | 1 | Open | 2025-04-15 | 5.2M |
| granite-speech-3.2 | ibm-granite | Speech→text | 8.5B | 1 | Open | 2025-03-26 | 62k |
| orpheus-0.1-ft | unsloth | Text→speech | 3.3B | 1 | Open | 2025-03-24 | 51k |
| orpheus-0.1-ft | canopylabs | Text→speech | 3.8B | 1 | Open | 2025-03-17 | 237k |
| indic-conformer-multilingual | ai4bharat | Speech→text | — | 1 | Open | 2025-03-15 | 66k |
| IndicF5 | ai4bharat | Text→speech | 351M | 1 | Open | 2025-03-11 | 27k |
| csm | sesame | Text→speech | 1.6B | 1 | Open | 2025-03-06 | 151k |
| Kokoro | mlx-community | Text→speech | — | 1 | Open | 2025-02-28 | 80k |
| Phi-4-multimodal | microsoft | Speech→text | 5.6B | 1 | Open | 2025-02-24 | 268k |
| kb-whisper-large | KBLab | Speech→text | 1.6B | 1 | Open | 2025-02-14 | 69k |
| Kokoro-ONNX | onnx-community | Text→speech | — | 1 | Open | 2025-02-07 | 1.1M |
| Zonos-transformer | Zyphra | Text→speech | 1.6B | 1 | Open | 2025-02-06 | 149k |
| TIGER-DnR | JusperLee | Audio→audio | 4M | 1 | Open | 2025-01-22 | 115k |
| Kokoro | hexgrad | Text→speech | — | 1 | Open | 2024-12-26 | 11.8M |
| diar_sortformer_4spk | nvidia | Speech→text | 124M | 1 | Licence fee | 2024-12-09 | 173k |
| parler-tts-mini-multilingual | parler-tts | Text→speech | 938M | 1 | Open | 2024-11-22 | 125k |
| indic-parler-tts | ai4bharat | Text→speech | 938M | 1 | Open | 2024-10-28 | 351k |
| MP-SENet-DNS | JacobLinCool | Audio→audio | 2M | 1 | Open | 2024-10-27 | 34k |
| E2-TTS | SWivid | Text→speech | — | 1 | Licence fee | 2024-10-14 | 168k |
| F5-TTS | SWivid | Text→speech | — | 1 | Licence fee | 2024-10-07 | 813k |
| whisper-large | openai | Speech→text | 809M | 2 | Open | 2024-10-01 | 7.3M |
| bigvgan_v2_44khz_128band_512x | nvidia | Audio→audio | — | 1 | Open | 2024-07-15 | 632k |
| bigvgan_v2_22khz_80band_256x | nvidia | Audio→audio | — | 1 | Open | 2024-07-15 | 2.2M |
| bigvgan_v2_24khz_100band_256x | nvidia | Audio→audio | — | 1 | Open | 2024-07-15 | 47k |
| SenseVoiceSmall | FunAudioLLM | Speech→text | — | 1 | Licence fee | 2024-07-03 | 33k |
| ellie-Bert-VITS2 | BricksDisplay | Text→speech | 397M | 1 | Open | 2024-06-13 | 52k |
| stable-audio-open-1.0 | stabilityai | Music / audio | 1.2B | 1 | Licence fee | 2024-05-24 | 21k |
| mms-1130-forced-aligner | MahmoudAshraf | Speech→text | 315M | 1 | Licence fee | 2024-05-02 | 2.5M |
| faster-distil-whisper-large | Systran | Speech→text | — | 1 | Open | 2024-03-25 | 44k |
| distil-large | distil-whisper | Speech→text | 756M | 1 | Open | 2024-03-21 | 723k |
| MeloTTS-Korean | myshell-ai | Text→speech | — | 1 | Open | 2024-02-29 | 86k |
| MeloTTS-Chinese | myshell-ai | Text→speech | — | 1 | Open | 2024-02-29 | 68k |
| MeloTTS-English | myshell-ai | Text→speech | — | 1 | Open | 2024-02-29 | 191k |
| whisperk-coreml | argmaxinc | Speech→text | — | 1 | Open | 2024-02-28 | 11.6M |
| nb-wav2vec2-bokmaal | NbAiLab | Speech→text | 963M | 1 | Open | 2024-02-02 | 758k |
| whisper-large | mlx-community | Speech→text | — | 1 | Open | 2024-01-07 | 33k |
| parakeet-ctc | nvidia | Speech→text | 1.1B | 1 | Open | 2023-12-28 | 1.7M |
| seamless-m4t-large | Speech→text | 2.3B | 1 | Licence fee | 2023-11-29 | 332k | |
| faster-whisper-small.en | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 489k |
| faster-whisper-tiny.en | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 683k |
| faster-whisper.en | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 416k |
| faster-whisper-small | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 2M |
| faster-whisper-tiny | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 1.9M |
| faster-whisper | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 1.6M |
| faster-whisper-medium.en | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 57k |
| faster-whisper-medium | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 632k |
| faster-whisper-large | Systran | Speech→text | — | 1 | Open | 2023-11-23 | 1.2M |
| speaker-diarization-3.1 | pyannote | Speech→text | — | 1 | Open | 2023-11-16 | 9.6M |
| XTTS | coqui | Text→speech | — | 1 | Licence fee | 2023-10-31 | 7.9M |
| speaker-diarization-3.0 | pyannote | Speech→text | — | 1 | Open | 2023-09-22 | 205k |
| mms-tts-bam | Text→speech | 36M | 1 | Licence fee | 2023-09-01 | 162k | |
| mms-tts-ara | Text→speech | 36M | 1 | Licence fee | 2023-09-01 | 65k | |
| mms-tts-hin | Text→speech | 36M | 1 | Licence fee | 2023-09-01 | 119k | |
| seamless-m4t-medium | Text→speech | — | 1 | Licence fee | 2023-08-28 | 115k | |
| mms-tts-eng | Text→speech | 36M | 1 | Licence fee | 2023-08-24 | 147k | |
| bark-small | suno | Text→speech | — | 1 | Open | 2023-07-18 | 29k |
| musicgen-large | Music / audio | — | 1 | Licence fee | 2023-06-08 | 90k | |
| musicgen-medium | Music / audio | — | 1 | Licence fee | 2023-06-08 | 1.9M | |
| musicgen-small | Music / audio | 591M | 1 | Licence fee | 2023-06-08 | 203k | |
| musicgen-melody | Music / audio | 1.6B | 1 | Licence fee | 2023-06-08 | 22k | |
| mms-all | Speech→text | 965M | 1 | Licence fee | 2023-05-27 | 255k | |
| bark | suno | Text→speech | — | 1 | Open | 2023-04-25 | 38k |
| speecht5_tts | microsoft | Text→speech | — | 1 | Open | 2023-02-02 | 54k |
| wav2vec2-vi-vlsp2020 | nguyenvulebinh | Speech→text | — | 1 | Licence fee | 2022-11-04 | 1.1M |
| tts-hifigan-libritts-22050Hz | speechbrain | Text→speech | — | 1 | Open | 2022-10-26 | 281k |
| whisper-medium.en | openai | Speech→text | 764M | 1 | Open | 2022-09-26 | 48k |
| whisper-small.en | openai | Speech→text | 242M | 1 | Open | 2022-09-26 | 78k |
| whisper.en | openai | Speech→text | 73M | 1 | Open | 2022-09-26 | 245k |
| whisper-tiny.en | openai | Speech→text | 38M | 1 | Open | 2022-09-26 | 237k |
| whisper-medium | openai | Speech→text | 764M | 1 | Open | 2022-09-26 | 365k |
| whisper-small | openai | Speech→text | 242M | 1 | Open | 2022-09-26 | 3M |
| whisper | openai | Speech→text | 73M | 1 | Open | 2022-09-26 | 1.8M |
| whisper-tiny | openai | Speech→text | 38M | 1 | Open | 2022-09-26 | 1.4M |
| nb-wav2vec2-nynorsk | NbAiLab | Speech→text | 963M | 1 | Open | 2022-06-09 | 970k |
| w2v-xls-r-uk | Yehor | Speech→text | 315M | 1 | Open | 2022-06-08 | 803k |
| wav2vec2-xls-r-mixed | mesolitica | Speech→text | — | 1 | Licence fee | 2022-06-01 | 1.1M |
| filipino-wav2vec2-l-xls-r-official | Khalsuu | Speech→text | — | 1 | Open | 2022-05-13 | 1.4M |
| wav2vec2-conformer-rope-large-960h-ft | Speech→text | 593M | 1 | Open | 2022-04-18 | 202k | |
| wav2vec2-large-xlsr-53-japanese | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 12.4M |
| wav2vec2-large-xlsr-53-portuguese | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 4.8M |
| voice-activity-detection | pyannote | Speech→text | — | 1 | Open | 2022-03-02 | 4.4M |
| wav2vec2-large-xlsr-53-russian | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 3.7M |
| wav2vec2-large-xlsr-53-polish | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 3.1M |
| wav2vec2-large-xlsr-53-dutch | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 2.6M |
| wav2vec2-indonesian-javanese-sundanese | indonesian-nlp | Speech→text | — | 1 | Open | 2022-03-02 | 2.5M |
| wav2vec2-large-xlsr-53-greek | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 2.2M |
| wav2vec2-large-xlsr-53-hungarian | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 1.8M |
| wav2vec2-large-xlsr-53-arabic | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 1.8M |
| wav2vec2-xls-r-cs-250 | comodoro | Speech→text | 315M | 1 | Open | 2022-03-02 | 1.6M |
| romanian-wav2vec2 | gigant | Speech→text | 315M | 1 | Open | 2022-03-02 | 1.6M |
| wav2vec2-large-xlsr-53-telugu | anuragshas | Speech→text | — | 1 | Open | 2022-03-02 | 1.5M |
| wav2vec2-large-xlsr-53-persian | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 1.4M |
| wav2vec2-960h | Speech→text | 94M | 1 | Open | 2022-03-02 | 1.4M | |
| wav2vec2-large-xlsr-53-chinese-zh-cn | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 1.3M |
| wav2vec2-large-xls-r-Urdu | kingabzpro | Speech→text | 315M | 1 | Open | 2022-03-02 | 1.3M |
| wav2vec2-large-xlsr-53-th | airesearch | Speech→text | — | 1 | Open | 2022-03-02 | 1.2M |
| Wav2Vec2-large-xlsr-hindi | theainerd | Speech→text | 316M | 1 | Licence fee | 2022-03-02 | 1.2M |
| wav2vec2-xls-r-hebrew | imvladikon | Speech→text | 315M | 1 | Licence fee | 2022-03-02 | 1.1M |
| wav2vec2-large-xlsr-korean | kresnik | Speech→text | 317M | 1 | Open | 2022-03-02 | 999k |
| wav2vec2-xls-r-bengali | arijitx | Speech→text | — | 1 | Open | 2022-03-02 | 934k |
| wav2vec2-large-xlsr-53-finnish | jonatasgrosman | Speech→text | — | 1 | Open | 2022-03-02 | 933k |
| wav2vec2-xls-r-parlaspeech-hr | classla | Speech→text | 315M | 1 | Licence fee | 2022-03-02 | 824k |
| wav2vec2-xlsr-nepali | gagan3012 | Speech→text | — | 1 | Open | 2022-03-02 | 771k |
| wav2vec2-large-xlsr-53-arabic | elgeish | Speech→text | — | 1 | Open | 2022-03-02 | 732k |
| wav2vec2-xlsr-53-espeak-cv-ft | Speech→text | — | 1 | Open | 2022-03-02 | 417k | |
| speaker-diarization | pyannote | Speech→text | — | 1 | Open | 2022-03-02 | 342k |
| wav2vec2-lv-60-espeak-cv-ft | Speech→text | — | 1 | Open | 2022-03-02 | 179k | |
| overlapped-speech-detection | pyannote | Speech→text | — | 1 | Open | 2022-03-02 | 31k |
| wav2vec2-large-voxrex-swedish | KBLab | Speech→text | 315M | 1 | Open | 2022-03-02 | 1.5M |
| vakyansh-wav2vec2-tamil-tam-250 | Harveenchadha | Speech→text | — | 1 | Open | 2022-03-02 | 1.1M |
Released is when the lead model was first published; downloads are HuggingFace 30-day pulls of the most popular variant — a popularity signal, not an AxForge metric. Licences are shown per model; several need a commercial agreement we can arrange for you.
Explore