π» CPUONNX~3 GB500M params
β¬ 263.0Kβ₯ 679text-to-speech
Audioapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16~2 GB500M params
β¬ 259.7Kβ₯ 1.3Ktext-to-speech
Audiomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 258.6Kβ₯ 1.6Kautomatic-speech-recognition
Audiomit
codemultilinguallicense:mit
View on Hugging Faceπ» CPUMLX
β¬ 248.1Kβ₯ 5automatic-speech-recognition
Audio
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 243.6Kβ₯ 18automatic-speech-recognition
Audioapache-2.0
dataset:arabic_speech_corpuslicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 242.7Kβ₯ 67automatic-speech-recognition
Audioapache-2.0
dataset:flozi00/asr-german-mixeddataset:flozi00/asr-german-mixed-evalslicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 238.6Kβ₯ 0automatic-speech-recognition
Audio
View on Hugging Faceπ» CPUONNX
β¬ 235.5Kβ₯ 40text-to-speech
Audioapache-2.0
license:apache-2.0
View on Hugging Faceβ‘ CPU/GPU
β¬ 233.3Kβ₯ 6text-to-speech
Audioapache-2.0
dataset:librittslicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 226.3Kβ₯ 12automatic-speech-recognition
Audioapache-2.0
dataset:common_voicelicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 226.3Kβ₯ 45automatic-speech-recognition
Audioapache-2.0
license:apache-2.0
View on Hugging Faceπ» CPUGGUF~1 GB600M params
β¬ 220.6Kβ₯ 639automatic-speech-recognition
Audioother
dataset:nvidia/granarydataset:ytcdataset:yodas2dataset:librilight
View on Hugging Faceπ» CPUMLX
β¬ 220.4Kβ₯ 9text-to-speech
Audioapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 210.3Kβ₯ 26audio-classification
Audioapache-2.0
dataset:xbgoose/dushalicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16~4 GB1.5B params
β¬ 204.0Kβ₯ 2.5Ktext-to-speech
Audiomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 198.9Kβ₯ 35audio-classification
Audioapache-2.0
license:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 172.6Kβ₯ 175audio-classification
Audiocc-by-nc-sa-4.0
dataset:msp-podcastlicense:cc-by-nc-sa-4.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 151.3Kβ₯ 32text-to-speech
Audioapache-2.0
license:apache-2.0
View on Hugging Faceβ‘ CPU/GPU
β¬ 147.0Kβ₯ 19audio-classification
Audiomit
dataset:commonvoicelicense:mit
View on Hugging Faceπ₯οΈ GPUFP16~17 GB7B paramsπ Gated
β¬ 144.2Kβ₯ 2.9Kaudio-to-audio
Audioother
license:other
View on Hugging Faceπ» CPUGGUF~1 GB300M params
β¬ 142.2Kβ₯ 7text-to-speech
Audiocc-by-nc-4.0
dataset:pnnbao-ump/vieneu-tts-1000hdataset:pnnbao-ump/vieneu-tts-140hlicense:cc-by-nc-4.0
View on Hugging Faceπ₯οΈ GPUFP16π Gated
β¬ 125.6Kβ₯ 509text-to-speech
Audioapache-2.0
dataset:ai4b-hf/globe-annotatedlicense:apache-2.0
View on Hugging Faceπ₯οΈ GPUFP16
β¬ 123.7Kβ₯ 316text-to-speech
Audiomit
license:mit
View on Hugging Faceπ₯οΈ GPUFP16~10 GB4B params
β¬ 123.5Kβ₯ 828text-to-speech
Audioother
license:other
View on Hugging Faceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
460 MBπ€ HF-backed
β¬ 1.1Kβ₯ 30automatic-speech-recognition
apache-2.0base: stt_fa_fastconformer_hybrid_large
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 0 seedersβ± stale
2.0 GBπ€ HF-backed
β¬ 1.0Kβ₯ 7text-to-speech
apache-2.0base: Kokoro-82M
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
SAFETENSORS3.1 GB1.5B paramsπ€ HF-backed
β¬ 1.0Kβ₯ 8automatic-speech-recognition
apache-2.0base: whisper-large-v3
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 13 seedersβ± stale
88 MBπ€ HF-backed
β¬ 1.0Kβ₯ 14text-to-speech
apache-2.0base: Kokoro-82M
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 0 seedersβ± stale
SAFETENSORS3.1 GB1.5B paramsπ€ HF-backed
β¬ 999β₯ 6automatic-speech-recognition
mitbase: whisper-large-v3
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
852 MB100M paramsπ€ HF-backed
β¬ 962β₯ 75text-to-speech
apache-2.0base: Audio8-TTS-Preview-0.1b
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
SAFETENSORS4.1 GB2.0B paramsπ€ HF-backed
β¬ 960β₯ 19automatic-speech-recognition
apache-2.0base: Qwen3-ASR-1.7B
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 4 seedersβ± stale
2.5 GB600M paramsπ€ HF-backed
β¬ 947β₯ 29automatic-speech-recognition
openmdw-1.1
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 1 seederβ± stale
3.8 GBπ€ HF-backed
β¬ 930β₯ 16automatic-speech-recognition
apache-2.0
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
312 MBπ€ HF-backed
β¬ 901β₯ 15audio-to-audio
apache-2.0base: neucodec
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 3 seeders
SAFETENSORS1.1 GB553M paramsπ€ HF-backed
β¬ 875β₯ 85text-to-speech
apache-2.0base: neutts-air
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
SAFETENSORS3.2 GB809M paramsπ€ HF-backed
β¬ 817β₯ 5automatic-speech-recognition
apache-2.0base: whisper-large-v3-turbo
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
SAFETENSORS491 MB123M paramsπ€ HF-backed
β¬ 803β₯ 19text-to-speech
apache-2.0base: ZipVoice
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
GGUF5.4 GBπ€ HF-backed
β¬ 773β₯ 3automatic-speech-recognition
apache-2.0base: Jais-ASR
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seeders
623 MBπ€ HF-backed
β¬ 761β₯ 18automatic-speech-recognition
mit
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
SAFETENSORS-600M paramsπ€ HF-backed
β¬ 752β₯ 2text-to-speech
mitbase: Qwen3-TTS-12Hz-0.6B-Base
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
1.6 GBπ€ HF-backed
β¬ 715β₯ 3automatic-speech-recognition
mitbase: whisper-large-v3-turbo
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 1 seederβ± stale
31 MBπ€ HF-backed
β¬ 702β₯ 39text-to-speech
apache-2.0
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seeders
SAFETENSORS3.1 GB1.5B paramsπ€ HF-backed
β¬ 686β₯ 3automatic-speech-recognition
mitbase: whisper-large-v3
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
SAFETENSORS1.3 GB315M paramsπ€ HF-backed
β¬ 632β₯ 3automatic-speech-recognition
apache-2.0
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 0 seedersβ± stale
SAFETENSORS3.1 GB1.5B paramsπ€ HF-backed
β¬ 614β₯ 4automatic-speech-recognition
mitbase: whisper-large-v3
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
GGUF657 MBπ€ HF-backed
β¬ 589β₯ 2automatic-speech-recognition
apache-2.0base: wav2vec2-large-xlsr-53-arabic
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceβ no seedersβ± stale
GGUF17 GBπ€ HF-backed
β¬ 581β₯ 35text-to-speech
apache-2.0
π΄ββ οΈ View on PirateFaceπ΄ββ οΈ PirateFaceπ± 0 seedersβ± stale
1.1 GBπ€ HF-backed
β¬ 580β₯ 62audio-classification
apache-2.0
π΄ββ οΈ View on PirateFace