README.md

metadata

library_name: transformers
language:
  - lv
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper medium LV - Felikss Kleins-{timestamp}
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17.0
          type: mozilla-foundation/common_voice_17_0
          config: lv
          split: None
          args: 'config: lv, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 10.601196845400864

Whisper medium LV - Felikss Kleins-{timestamp}

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2428
• Wer: 10.6012

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.02	200	0.2930	22.3576
0.9797	1.0116	400	0.2359	18.2083
0.357	2.0033	600	0.2274	16.4665
0.2582	2.0233	800	0.2111	15.6402
0.1718	3.0149	1000	0.2135	14.9883
0.1718	4.0066	1200	0.2090	14.2294
0.1355	4.0266	1400	0.2193	13.5537
0.1024	5.0183	1600	0.2255	14.5048
0.0836	6.0099	1800	0.2145	12.9751
0.0699	7.0015	2000	0.2232	13.2129
0.0699	7.0216	2200	0.2181	12.7155
0.0598	8.0132	2400	0.2192	12.7076
0.054	9.0048	2600	0.2348	13.0048
0.0452	9.0249	2800	0.2241	13.0940
0.0433	10.0165	3000	0.2406	12.6362
0.0433	11.0082	3200	0.2283	12.5332
0.0377	11.0282	3400	0.2293	12.2201
0.0317	12.0198	3600	0.2323	12.6144
0.0297	13.0114	3800	0.2309	12.2974
0.0267	14.0031	4000	0.2342	11.9011
0.0267	14.0231	4200	0.2286	12.1171
0.0243	15.0147	4400	0.2364	12.0854
0.0218	16.0064	4600	0.2405	12.1805
0.021	16.0264	4800	0.2422	12.0338
0.0173	17.0180	5000	0.2416	11.9387
0.0173	18.0097	5200	0.2421	12.0180
0.0175	19.0013	5400	0.2385	11.6613
0.0161	19.0214	5600	0.2442	11.9090
0.0136	20.013	5800	0.2411	11.4513
0.0135	21.0047	6000	0.2470	12.0418
0.0135	21.0247	6200	0.2446	11.5246
0.0117	22.0163	6400	0.2466	11.7386
0.0111	23.0080	6600	0.2498	12.0715
0.01	23.0280	6800	0.2487	12.0596
0.0094	24.0196	7000	0.2431	11.4315
0.0094	25.0113	7200	0.2460	11.5702
0.009	26.0029	7400	0.2436	11.2293
0.0077	26.0229	7600	0.2467	11.3423
0.007	27.0145	7800	0.2439	11.0054
0.0071	28.0062	8000	0.2430	11.1996
0.0071	28.0262	8200	0.2458	11.1798
0.0063	29.0178	8400	0.2456	11.0847
0.0049	30.0095	8600	0.2450	11.1303
0.0049	31.0011	8800	0.2467	11.0530
0.0053	31.0211	9000	0.2448	11.1085
0.0053	32.0128	9200	0.2467	11.2650
0.0041	33.0044	9400	0.2444	11.0728
0.0045	33.0245	9600	0.2426	10.6547
0.0036	34.0161	9800	0.2427	10.5972
0.004	35.0078	10000	0.2428	10.6012

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.0.1
• Datasets 3.0.0
• Tokenizers 0.19.1