Rafael Vasconcelos
playmak3r
AI & ML interests
None yet
Recent Activity
liked a model about 10 hours ago
GAIR/daVinci-MagiHuman liked a model 2 days ago
linyq/kiwi-edit-5b-instruct-only-diffusers liked a model 2 days ago
syxbb/SAMA-14BOrganizations
None yet
WebGPU
- RunningFeatured1.24k
Whisper Web
π€1.24kTranscribe audio files to readable text instantly
-
onnx-community/whisper-large-v3-turbo
Automatic Speech Recognition β’ Updated β’ 10.2k β’ 70 -
onnx-community/whisper-large-v3-turbo_timestamped
Automatic Speech Recognition β’ Updated β’ 3.19k β’ 10 - RunningFeatured10
Granite Speech WebGPU
π10Transcribe or translate spoken audio to text in your browser
Heavier TTS Models
Good models, but larger, with no way of using them on cpu
- Running on ZeroFeatured2.83k
F5-TTS
π£2.83kF5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
- Runtime errorFeatured699
Fish Audio S1
π699Convert text to natural-sounding speech audio
- Running on Zero779
IndexTTS 2 Demo
π’779Generate expressive speech audio from text with emotion control
-
OpenMOSS-Team/MOSS-TTS
Text-to-Speech β’ 8B β’ Updated β’ 91.5k β’ 351
Study
lightweight models
-
AIDC-AI/Marco-o1
Text Generation β’ 8B β’ Updated β’ 380 β’ β’ 711 -
CohereLabs/aya-expanse-8b
Text Generation β’ 8B β’ Updated β’ 15.6k β’ 422 -
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any β’ 35B β’ Updated β’ 382k β’ 870 -
Qwen/Qwen3-30B-A3B-Thinking-2507
Text Generation β’ 31B β’ Updated β’ 1.1M β’ β’ 370
Awesome TTS
Spaces providing very good TTS models
3D
Study
WebGPU
- RunningFeatured1.24k
Whisper Web
π€1.24kTranscribe audio files to readable text instantly
-
onnx-community/whisper-large-v3-turbo
Automatic Speech Recognition β’ Updated β’ 10.2k β’ 70 -
onnx-community/whisper-large-v3-turbo_timestamped
Automatic Speech Recognition β’ Updated β’ 3.19k β’ 10 - RunningFeatured10
Granite Speech WebGPU
π10Transcribe or translate spoken audio to text in your browser
lightweight models
-
AIDC-AI/Marco-o1
Text Generation β’ 8B β’ Updated β’ 380 β’ β’ 711 -
CohereLabs/aya-expanse-8b
Text Generation β’ 8B β’ Updated β’ 15.6k β’ 422 -
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any β’ 35B β’ Updated β’ 382k β’ 870 -
Qwen/Qwen3-30B-A3B-Thinking-2507
Text Generation β’ 31B β’ Updated β’ 1.1M β’ β’ 370
Heavier TTS Models
Good models, but larger, with no way of using them on cpu
- Running on ZeroFeatured2.83k
F5-TTS
π£2.83kF5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
- Runtime errorFeatured699
Fish Audio S1
π699Convert text to natural-sounding speech audio
- Running on Zero779
IndexTTS 2 Demo
π’779Generate expressive speech audio from text with emotion control
-
OpenMOSS-Team/MOSS-TTS
Text-to-Speech β’ 8B β’ Updated β’ 91.5k β’ 351
Awesome TTS
Spaces providing very good TTS models