stt 2.6b en trfs EU AI Act Compliance Profile

Model Card for Kyutai STT

This repo is meant to use the model with Transformers 🤗

Starting with transformers >= 4.53.0 and above, you can now run Kyutai STT natively!

pip install -U transformers

Inference:

import torch
from datasets import load_dataset, Audio
from transformers import KyutaiSpeechToTextProcessor, KyutaiSpeechToTextForConditionalGeneration

# 1. load the model and the processor
torch_device = "cuda" if torch.cuda.is_available() else "cpu"
model_id = "kyutai/stt-2.6b-en-trfs"

processor = KyutaiSpeechToTextProcessor.from_pretrained(model_id)
model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device, torch_dtype="auto")

# 2. load audio samples
ds = load_dataset(
    "hf-internal-testing/librispeech_asr_dummy", "clean", split="validation"
)
ds = ds.cast_column("audio", Audio(sampling_rate=24000))

# 3. prepare the model inputs
inputs = processor(
    ds[0]["audio"]["array"],
)
inputs.to(torch_device)

# 4. infer the model
output_tokens = model.generate(**inputs)

# 5. decode the generated tokens
print(processor.batch_decode(output_tokens, skip_special_tokens=True))

Batched inference:

import torch
from datasets import load_dataset, Audio
from transformers import KyutaiSpeechToTextProcessor, KyutaiSpeechToTextForConditionalGeneration

# 1. load the model and the processor
torch_device = "cuda" if torch.cuda.is_available() else "cpu"
model_id = "kyutai/stt-2.6b-en-trfs"

processor = KyutaiSpeechToTextProcessor.from_pretrained(model_id)
model = KyutaiSpeechToTextForConditionalGeneration.from_pretrained(model_id, device_map=torch_device, torch_dtype="auto")

# 2. load audio samples
ds = load_dataset(
    "hf-internal-testing/librispeech_asr_dummy", "clean", split="validation"
)
ds = ds.cast_column("audio", Audio(sampling_rate=24000))

# 3. prepare the model inputs
audio_arrays = [ds[i]["audio"]["array"] for i in range(4)]
inp

Your obligations as a stt 2.6b en trfs deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library