LFM2-Audio-1.5B

1.5B audio model (deprecated - use LFM2.5-Audio-1.5B instead)

← Back to Audio Models

This model is deprecated. Use LFM2.5-Audio-1.5B for improved ASR, TTS, and CPU-friendly inference.

LFM2-Audio-1.5B was the original fully interleaved audio/text model. It has been superseded by LFM2.5-Audio-1.5B, which features a custom LFM-based audio detokenizer and improved performance.

HFGGUF

Specifications

Property	Value
Parameters	1.5B (1.2B LM + 115M audio encoder)
Context Length	32K tokens
Audio Output	24kHz (Mimi codec)
Supported Language	English

Quick Start

liquid-audio

Install:

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

Gradio Demo:

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

Multi-Turn Chat:

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

# Load models
HF_REPO = "LiquidAI/LFM2-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 (Mimi returns audio at 24kHz)
mimi_codes = torch.stack(audio_out[:-1], 1).unsqueeze(0)
with torch.no_grad():
    waveform = processor.mimi.decode(mimi_codes)[0]
torchaudio.save("answer.wav", waveform.cpu(), 24_000)

llama.cpp

Setup:

export CKPT=/path/to/LFM2-Audio-1.5B-GGUF
export INPUT_WAV=/path/to/input.wav
export OUTPUT_WAV=/path/to/output.wav

ASR (Audio to Text):

./llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf \
  --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf \
  -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf \
  -sys "Perform ASR." --audio $INPUT_WAV

TTS (Text to Audio):

./llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf \
  --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf \
  -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf \
  -sys "Perform TTS." \
  -p "What is this obsession people have with books?" \
  --output $OUTPUT_WAV

Interleaved Mode:

./llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf \
  --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf \
  -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf \
  -sys "Respond with interleaved text and audio." \
  --audio $INPUT_WAV --output $OUTPUT_WAV

Runners are available for macos-arm64, ubuntu-arm64, ubuntu-x64, and android-arm64.