|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- audio-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2vec2-base_than_I_did |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# wav2vec2-base_than_I_did |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the MatsRooth/than_I_did dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2077 |
|
- Accuracy: 0.9592 |
|
|
|
## Model description |
|
|
|
This is a binary classifier for the prosody of tokens of "I did". The label s is subject prominence. The label |
|
ns is the complement, with prominence either on "did" or afterwards. |
|
|
|
## Intended uses & limitations |
|
|
|
Research on prosody. |
|
|
|
## Training and evaluation data |
|
|
|
The utterances are collected on Youtube, aligned with the Youtube transcript using Kaldi, and cut to the |
|
words "I did" using Matlab. Labels were assigned by the experimenter, using 's' for tokens there the main clause |
|
subject differed from the than-clause subject, and 'ns' for other tokens. The labeling does not depend on prosody, |
|
though it correlates with it. |
|
|
|
On the same problem using an SVM classifier, see Howell, Jonathan, Mats Rooth, and Michael Wagner, *Acoustic classification of focus: On the web and in the lab* (2016). |
|
|
|
The class ns was reduced to 160 tokens, to match the number of tokens of s. |
|
|
|
## Training procedure |
|
Training and evaluation use run_audio_classification.py from HuggingFace. The slurm script than_I_did.sub launches training. |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 3e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 0 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 20.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 0.94 | 8 | 0.6940 | 0.4694 | |
|
| 0.6939 | 2.0 | 17 | 0.6776 | 0.6735 | |
|
| 0.6844 | 2.94 | 25 | 0.6505 | 0.6531 | |
|
| 0.6752 | 4.0 | 34 | 0.6390 | 0.6122 | |
|
| 0.6071 | 4.94 | 42 | 0.5664 | 0.7959 | |
|
| 0.5483 | 6.0 | 51 | 0.4090 | 0.8571 | |
|
| 0.5483 | 6.94 | 59 | 0.3948 | 0.8163 | |
|
| 0.4747 | 8.0 | 68 | 0.4082 | 0.8163 | |
|
| 0.4782 | 8.94 | 76 | 0.3435 | 0.8776 | |
|
| 0.4403 | 10.0 | 85 | 0.3410 | 0.8776 | |
|
| 0.4682 | 10.94 | 93 | 0.2878 | 0.8980 | |
|
| 0.4032 | 12.0 | 102 | 0.2589 | 0.9184 | |
|
| 0.359 | 12.94 | 110 | 0.2554 | 0.9184 | |
|
| 0.359 | 14.0 | 119 | 0.2077 | 0.9592 | |
|
| 0.3142 | 14.94 | 127 | 0.1839 | 0.9592 | |
|
| 0.3735 | 16.0 | 136 | 0.1944 | 0.9388 | |
|
| 0.3655 | 16.94 | 144 | 0.1870 | 0.9592 | |
|
| 0.3918 | 18.0 | 153 | 0.2005 | 0.9592 | |
|
| 0.3305 | 18.82 | 160 | 0.1947 | 0.9592 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.15.0 |
|
|
