Model Card for Model ID
This modelcard aims to be a base template for new models. It has been generated using this raw template.
Model Details
The model has 31,536,128 trainable parameters
Model Description
Model trained using Early Exit architecture: 12 conformer layers, 6 CTC decoders. The model has been generated by averaging from epoch 60 to epoch 90. This model can handle only speech signals sampled at 16 kHz.
Uses
To be used for ASR: code for using the model available at https://github.com/SpeechTechLab/early-exit-transformer
How to Get Started with the Model
Use the code at https://github.com/SpeechTechLab/early-exit-transformer
Training Details
decoder_mode='ctc', model_type='early_conformer', bpe=True
distill=False, language_model=None, language_model_dict=None, avg_model_start=60, avg_model_end=90
max_len=2000, d_model=256, n_enc_layers_per_exit=2, n_enc_exits=6, n_dec_layers=6, n_heads=8
d_feed_forward=2048, depthwise_kernel_size=31, max_utterance_length=600, sample_rate=16000
n_fft=512, win_length=320, hop_length=160, n_mels=80
src_pad_idx=0, trg_pad_idx=126, trg_sos_idx=1, trg_eos_idx=2, enc_voc_size=256, dec_voc_size=256
sp=<sentencepiece.SentencePieceProcessor=;'aiXpa_en.bpe-256.model' lexicon='aiXpa_en-bpe-256.lex', tokens='aiXpa_en-bpe-256.tok')
Training Data
LibriSpeech, Voxpopuli, TEDLIUM release 3
Training Procedure
From scratch
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
shuffle=True, batch_size=64, n_batch_split=8, drop_prob=0.1, init_lr=1e-05, adam_eps=1e-09, weight_decay=0.0001, warmup=[trining dataset size], clip=1.0
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation (%WER)
| test-clean | Voxpopuli | TEDLIUM |
|---|---|---|
| 6.73 | 13.12 | 11.97 |
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
FBK - digis cluster
Hardware
device=device(type='cuda', index=0, CUDA Version: 12.5) GPU quadro RTX50000
Software
[More Information Needed]
Citation [optional]
G. A. Wright, U. Cappellazzo, S. Zaiem, D. Raj, L. O. Yang, D. Falavigna, M. N. Ali, and A. Brutti, “Training early-exit architectures for automatic speech recognition: Fine-tuning pre-trained models or training from scratch,” in Proc. of ICASSP Workshops, 2024, pp. 685–689.
Maxence Lasbordes, Daniele Falavigna, Alessio Brutti, “Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices”, Proc. of EUSIPCO 2025 (https://arxiv.org/abs/2506.18035)
Mohamed Nabih Ali, Alessio Brutti, Daniele Falavigna, Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients. To appear on "Progress in Artificial Intelligence" (https://arxiv.org/abs/2405.17376)
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]