Granite Speech 3.2 8b

🚀 Granite-speech-3.2-8b

Granite-speech-3.2-8b is a compact and efficient speech-language model designed for automatic speech recognition (ASR) and automatic speech translation (AST). It uses a two-pass design, offering unique processing capabilities.

🚀 Quick Start

Installation

First, make sure to build the latest version of transformers:

pip install transformers>=4.49 peft torchaudio

Install a torchaudio backend, such as:

pip install soundfile

Usage

import torch
import torchaudio
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
from huggingface_hub import hf_hub_download

device = "cuda" if torch.cuda.is_available() else "cpu"

model_name = "ibm-granite/granite-speech-3.2-8b"
speech_granite_processor = AutoProcessor.from_pretrained(
    model_name, trust_remote_code=True)
tokenizer = speech_granite_processor.tokenizer
speech_granite = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_name, trust_remote_code=True).to(device)

# prepare speech and text prompt, using the appropriate prompt template

audio_path = hf_hub_download(repo_id=model_name, filename='10226_10111_000000.wav')
wav, sr = torchaudio.load(audio_path, normalize=True)
assert wav.shape[0] == 1 and sr == 16000 # mono, 16khz

# create text prompt
chat = [
    {
        "role": "system",
        "content": "Knowledge Cutoff Date: April 2024.\nToday's Date: December 19, 2024.\nYou are Granite, developed by IBM. You are a helpful AI assistant",
    },
    {
        "role": "user",
        "content": "<|audio|>can you transcribe the speech into a written format?",
    }
]

text = tokenizer.apply_chat_template(
    chat, tokenize=False, add_generation_prompt=True
)

# compute audio embeddings
model_inputs = speech_granite_processor(
    text,
    wav,
    device=device, # Computation device; returned tensors are put on CPU
    return_tensors="pt",
).to(device)
 
model_outputs = speech_granite.generate(
    **model_inputs,
    max_new_tokens=200,
    num_beams=4,
    do_sample=False,
    min_length=1,
    top_p=1.0,
    repetition_penalty=1.0,
    length_penalty=1.0,
    temperature=1.0,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.pad_token_id,
)

# Transformers includes the input IDs in the response.
num_input_tokens = model_inputs["input_ids"].shape[-1]
new_tokens = torch.unsqueeze(model_outputs[0, num_input_tokens:], dim=0)

output_text = tokenizer.batch_decode(
    new_tokens, add_special_tokens=False, skip_special_tokens=True
)
print(f"STT output = {output_text[0].upper()}")

✨ Features

• Two - pass Design: Unlike integrated models, Granite - speech - 3.2 - 8b uses a two - pass design. Initial calls transcribe audio files into text, and a second call is needed to process the transcribed text using the underlying Granite language model.
• Diverse Training Data: Trained on a collection of public corpora, including diverse datasets for ASR and AST, as well as synthetic datasets tailored for speech translation.
• Modular Design for Safety: The model's modular design limits how audio inputs can influence the system, minimizing the risk of adversarial inputs.

📚 Documentation

Model Summary

Granite - speech - 3.2 - 8b is a compact and efficient speech - language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST). It uses a two - pass design. Initial calls to granite - speech - 3.2 - 8b will transcribe audio files into text. To process the transcribed text using the underlying Granite language model, users must make a second call as each step must be explicitly initiated.

The model was trained on a collection of public corpora comprising diverse datasets for ASR and AST as well as synthetic datasets tailored to support the speech translation task. Granite - speech - 3.2 was trained by modality aligning granite - 3.2 - 8b - instruct (https://huggingface.co/ibm - granite/granite - 3.2 - 8b - instruct) to speech on publicly available open source corpora containing audio inputs and text targets.

Evaluations

We evaluated granite - speech - 3.2 - 8b alongside other speech - language models (SLMs) in the less than 8b parameter range as well as dedicated ASR and AST systems on standard benchmarks. The evaluation spanned multiple public benchmarks, with particular emphasis on English ASR tasks while also including AST for En - X translation.




Model Architecture

The architecture of granite - speech - 3.2 - 8b consists of the following components:

(1) Speech encoder: 10 conformer blocks trained with Connectionist Temporal Classification (CTC) on character - level targets on the subset containing only ASR corpora (see configuration below). In addition, our CTC encoder uses block - attention with 4 - seconds audio blocks and self - conditioned CTC from the middle layer.

(2) Speech projector and temporal downsampler (speech - text modality adapter): we use a 2 - layer window query transformer (q - former) operating on blocks of 15 1024 - dimensional acoustic embeddings coming out of the last conformer block of the speech encoder that get downsampled by a factor of 5 using 3 trainable queries per block and per layer. The total temporal downsampling factor is 10 (2x from the encoder and 5x from the projector) resulting in a 10Hz acoustic embeddings rate for the LLM. The encoder, projector and LoRA adapters were fine - tuned/trained jointly on all the corpora mentioned under Training Data.

(3) Large language model: granite - 3.2 - 8b - instruct with 128k context length (https://huggingface.co/ibm - granite/granite - 3.2 - 8b - instruct).

(4) LoRA adapters: rank = 64 applied to the query, value projection matrices

Training Data

Overall, our training data is largely comprised of two key sources: (1) publicly available datasets (2) Synthetic data created from publicly available datasets specifically targeting the speech translation task. A detailed description of the training datasets can be found in the table below:

Infrastructure

We train Granite Speech using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs. The training of this particular model was completed in 10 days on 32 H100 GPUs.

Ethical Considerations and Limitations

The use of Large Speech and Language Models may involve risks and ethical considerations that people should be aware of. These risks may include bias and fairness, misinformation, and autonomous decision - making. We urge the community to use granite - speech - 3.2 - 8b in a manner consistent with IBM's Responsible Use Guide or similar responsible use structures. IBM recommends using this model for automatic speech recognition tasks. The model's modular design improves safety by limiting how audio inputs can influence the system. If an unfamiliar or malformed prompt is received, the model simply echoes it with its transcription. This minimizes the risk of adversarial inputs, unlike integrated models that directly interpret audio and may be more exposed to such attacks. Note that more general speech tasks may pose higher inherent risks of triggering unwanted outputs.

To enhance safety, we recommend using granite - speech - 3.2 - 8b alongside Granite Guardian. Granite Guardian is a fine - tuned instruct model designed to detect and flag risks in prompts and responses across key dimensions outlined in the IBM AI Risk Atlas. Its training, which includes both human - annotated and synthetic data informed by internal red - teaming, enables it to outperform similar open - source models on standard benchmarks, providing an additional layer of safety.

📄 License

This project is licensed under the [Apache 2.0](https://www.apache.org/licenses/LICENSE - 2.0) license.

Resources

• ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
• 🚀 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
• 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite - learning - resources