metadata
license: mit
inference: false
A simple use case:
from transformers import Wav2Vec2Processor, HubertModel
import torch
from torch import nn
from datasets import load_dataset
# load demo audio and set processor
dataset = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
dataset = dataset.sort("id")
sampling_rate = dataset.features["audio"].sampling_rate
processor = Wav2Vec2Processor.from_pretrained("facebook/hubert-large-ls960-ft")
# loading our model weights
model = HubertModel.from_pretrained("m-a-p/MERT-v0")
# audio file is decoded on the fly
inputs = processor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs, output_hidden_states=True)
# take a look at the output shape, there are 13 layers of representation
# each layer performs differently in different downstream tasks, you should choose empirically
all_layer_hidden_states = torch.stack(outputs.hidden_states).squeeze()
print(all_layer_hidden_states.shape) # [13 layer, 292 timestep, 768 feature_dim]
# for utterance level classification tasks, you can simply reduce the representation in time
time_reduced_hidden_states = all_layer_hidden_states.mean(-2)
print(time_reduced_hidden_states.shape) # [13, 768]
# you can even use a learnable weighted average representation
aggregator = nn.Conv1d(in_channels=13, out_channels=1, kernel_size=1)
weighted_avg_hidden_states = aggregator(time_reduced_hidden_states.unsqueeze(0)).squeeze()
print(weighted_avg_hidden_states.shape) # [768]