LFM2.5-Audio-1.5B

pip install liquid-audio
pip install "liquid-audio[demo]"  # optional, for demo dependencies
pip install flash-attn --no-build-isolation  # optional, for flash attention 2

liquid-audio-demo
# Starts webserver on http://localhost:7860/

import torch
import torchaudio
from liquid_audio import LFM2AudioModel, LFM2AudioProcessor, ChatState

# Load models
HF_REPO = "LiquidAI/LFM2.5-Audio-1.5B"
processor = LFM2AudioProcessor.from_pretrained(HF_REPO).eval()
model = LFM2AudioModel.from_pretrained(HF_REPO).eval()

# Set up chat
chat = ChatState(processor)
chat.new_turn("system")
chat.add_text("Respond with interleaved text and audio.")
chat.end_turn()

chat.new_turn("user")
wav, sampling_rate = torchaudio.load("question.wav")
chat.add_audio(wav, sampling_rate)
chat.end_turn()

chat.new_turn("assistant")

# Generate text and audio tokens
text_out, audio_out = [], []
for t in model.generate_interleaved(**chat, max_new_tokens=512, audio_temperature=1.0, audio_top_k=4):
    if t.numel() == 1:
        print(processor.text.decode(t), end="", flush=True)
        text_out.append(t)
    else:
        audio_out.append(t)

# Detokenize audio and save
audio_codes = torch.stack(audio_out[:-1], 1).unsqueeze(0)
waveform = processor.decode(audio_codes)
torchaudio.save("answer.wav", waveform.cpu(), 24_000)