metadata

base_model: facebook/mms-1b-all
datasets:
  - common_voice_17_0
library_name: transformers
license: cc-by-nc-4.0
metrics:
  - wer
  - bleu
tags:
  - generated_from_trainer
model-index:
  - name: wav2vec2-mms-1b-CV17.0-training_set_variations
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: ta
          split: validation
          args: ta
        metrics:
          - type: wer
            value: 0.4582664894348444
            name: Wer
          - type: bleu
            value: 0.3001349308741465
            name: Bleu

wav2vec2-mms-1b-CV17.0-training_set_variations

This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.4355
Wer: 0.4583
Cer: 0.0787
Bleu: 0.3001

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 16
eval_batch_size: 8
seed: 42
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: 0.15
training_steps: 2000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Bleu
12.8763	25.0	50	4.9690	1.0000	0.9319	0.0
2.2038	50.0	100	0.3040	0.4239	0.0696	0.3337
0.1153	75.0	150	0.2911	0.4134	0.0685	0.3474
0.0557	100.0	200	0.3344	0.4333	0.0718	0.3271
0.0448	125.0	250	0.3486	0.4403	0.0743	0.3213
0.0382	150.0	300	0.3938	0.4499	0.0762	0.3102
0.0364	175.0	350	0.3927	0.4525	0.0778	0.3045
0.0286	200.0	400	0.3883	0.4417	0.0744	0.3173
0.0293	225.0	450	0.4235	0.4656	0.0794	0.2913
0.0296	250.0	500	0.4432	0.4710	0.0817	0.2771
0.0302	275.0	550	0.4266	0.4524	0.0765	0.3016
0.0252	300.0	600	0.4376	0.4717	0.0815	0.2793
0.0216	325.0	650	0.4355	0.4583	0.0787	0.3001

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1