HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated • 322 • 30
Audio & Voice
-
-
nari-labs/Dia-1.6B
Text-to-Speech • Updated • 115k • • 2.83k -
Whisper-WebUI
🚀41Generate subtitles and translate audio files
-
Nllb Translation
📈2Translate text between multiple languages
-
facebook/nllb-200-3.3B
Translation • Updated • 60.2k • 435 -
NLLB
🌐176Translate text between 200 languages instantly
-
MMS
🌍14Transcribe audio to text in multiple languages
-
StyleTTS 2
🗣725Efficient, fast, and natural text to speech with StyleTTS 2!
-
MOSS Transcribe Diarize
🏢56Transcribe audio/video with speaker diarization
-
pyannote/segmentation
Voice Activity Detection • Updated • 2.12M • 670 -
pyannote/speaker-diarization
Automatic Speech Recognition • Updated • 760k • 1.25k -
mythicinfinity/libritts
Viewer • Updated • 756k • 2.67k • 27 -
fierce-cats/beatrice-trainer
Audio-to-Audio • Updated • 39 -
Qwen/Qwen3-TTS-12Hz-1.7B-Base
Updated • 1.66M • 357 -
Seed Voice Conversion
🎤474Convert speech to another voice instantly
-
Ultimate RVC
💙124The Ultimate RVC Project
-
Dia 1.6B
👯1.76kGenerate realistic dialogue from a script, using Dia!
-
nari-labs/Dia-1.6B-0626
Text-to-Speech • 2B • Updated • 9.56k • 129 -
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
Paper • 2505.13032 • Published • 4
