Chatterbox TTS - Español Rioplatense (LoRA Fine-tuned)
Este modelo es una versión fine-tuneada de ResembleAI/chatterbox-multilingual usando LoRA para generar voz con acento argentino/rioplatense.
Uso
from chatterbox.tts import ChatterboxTTS
# Cargar modelo
model = ChatterboxTTS.from_pretrained("franclarke/chatterbox-es-ar")
# Generar audio
text = "Che, me voy al laburo en bondi."
wav = model.generate(text, lang="es")
# Guardar
import soundfile as sf
sf.write("output.wav", wav, 24000)
Entrenamiento
- Dataset: Orpheus LATAM (AR)
- Método: LoRA (Low-Rank Adaptation)
- Código: github.com/franclarke/chatterbox-es-latam
Licencia
Apache 2.0
- Downloads last month
- -
Model tree for franclarke/chatterbox-es-ar
Base model
ResembleAI/chatterbox
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr)