metadata
license: other
language:
- te
- en
pipeline_tag: text-to-speech
tags:
- text-to-speech
- telugu
- higgs-audio
- voice-avatar
- code-switch
base_model: bosonai/higgs-audio-v3-tts-4b
Higgs Audio v3 — Telugu single-speaker voice (ISO-romanized fine-tune)
Expressive single-speaker Telugu (code-switch) TTS, fine-tuned from Higgs Audio v3 (4B). Generates this speaker's voice from text with no reference clip.
Frontend matters: Telugu text must be ISO-15919 romanized with the same
frontend.py used in training (Telugu tokenizes to byte-fragments otherwise).
generate_speech handles the rest.
import torch, torchaudio
from transformers import AutoModelForCausalLM, AutoTokenizer
from frontend import romanize # shipped in this repo
repo = "BNarayanaReddy/higgs-telugu-e5-lora-epoch_6"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True,
dtype=torch.bfloat16).to("cuda").eval()
text = "హలో, ఈ రోజు ఎలా ఉన్నారు?"
wav = model.generate_speech(romanize(text, "iso"), tok, temperature=0.7, top_p=0.95)
torchaudio.save("out.wav", wav.unsqueeze(0), model.config.sample_rate)
Run #1 of an ISO-romanized single-speaker adaptation. Research use.