SpeechLLM

SpeechLLM is a multi-modal LLM trained to predict the metadata of the speaker's turn in a conversation. speechllm-2B model is based on HubertX audio encoder and TinyLlama LLM. The model predicts the following:

1. SpeechActivity : if the audio signal contains speech (True/False)
2. Transcript : ASR transcript of the audio
3. Gender of the speaker (Female/Male)
4. Age of the speaker (Young/Middle-Age/Senior)
5. Accent of the speaker (Africa/America/Celtic/Europe/Oceania/South-Asia/South-East-Asia)
6. Emotion of the speaker (Happy/Sad/Anger/Neutral/Frustrated)

Usage

# Load model directly from huggingface
from transformers import AutoModel
model = AutoModel.from_pretrained("skit-ai/speechllm-1.5B", trust_remote_code=True)

model.generate_meta(
	audio_path="path-to-audio.wav", #16k Hz, mono
    audio_tensor=torchaudio.load("path-to-audio.wav")[1], # [Optional] either audio_path or audio_tensor directly
	instruction="Give me the following information about the audio [SpeechActivity, Transcript, Gender, Emotion, Age, Accent]",
	max_new_tokens=500, 
	return_special_tokens=False
)

# Model Generation
'''
{
  "SpeechActivity" : "True",
  "Transcript": "Yes, I got it. I'll make the payment now.",
  "Gender": "Female",
  "Emotion": "Neutral",
  "Age": "Young",
  "Accent" : "America",
}
'''

Try the model in Google Colab Notebook. Also, check out our blog on SpeechLLM for end-to-end conversational agents(User Speech -> Response).

Model Details

• Developed by: Skit AI
• Authors: Shangeth Rajaa, Abhinav Tushar
• Language: English
• Finetuned from model: WavLM, TinyLlama
• Model Size: 1.5 B
• Checkpoint: 1200 k steps (bs=1)
• Adapters: r=8, alpha=16
• lr : 1e-4
• gradient accumulation steps: 8

Checkpoint Result

Cite

@misc{Rajaa_SpeechLLM_Multi-Modal_LLM,
author = {Rajaa, Shangeth and Tushar, Abhinav},
title = {{SpeechLLM: Multi-Modal LLM for Speech Understanding}},
url = {https://github.com/skit-ai/SpeechLLM}
}