README.md

metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
metrics:
  - wer
model-index:
  - name: whisper-tiny_en
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: PolyAI/minds14
          type: PolyAI/minds14
          config: en-US
          split: train
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 34.56072351421189

whisper-tiny_en

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5991
• Wer Ortho: 36.0700
• Wer: 34.5607

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: 1e-06
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
4.3106	0.89	25	4.5196	51.0094	36.6925
3.9031	1.79	50	3.5872	51.0094	37.0155
2.9832	2.68	75	2.8616	48.9906	36.7571
2.3893	3.57	100	2.3230	47.1063	37.0155
1.9074	4.46	125	1.8030	44.6837	36.8863
1.3515	5.36	150	1.3467	43.5397	37.1447
0.9984	6.25	175	0.9622	42.6649	37.0155
0.7155	7.14	200	0.7915	42.1265	37.1447
0.6152	8.04	225	0.7200	41.1844	37.1447
0.523	8.93	250	0.6814	40.9152	37.1447
0.4744	9.82	275	0.6561	39.2328	35.8527
0.4411	10.71	300	0.6371	40.4441	37.4031
0.3926	11.61	325	0.6194	37.5505	35.2067
0.3855	12.5	350	0.6111	37.2140	35.0775
0.3709	13.39	375	0.6012	37.3486	35.1421
0.3315	14.29	400	0.5963	37.3486	35.2713
0.3113	15.18	425	0.5892	37.2813	35.4005
0.3112	16.07	450	0.5849	37.3486	35.4005
0.2809	16.96	475	0.5827	36.6756	34.7545
0.2694	17.86	500	0.5778	36.8775	34.9483
0.236	18.75	525	0.5775	36.2046	34.2377
0.2512	19.64	550	0.5755	36.6756	34.6899
0.2154	20.54	575	0.5760	36.2046	34.3023
0.2174	21.43	600	0.5742	36.0027	34.1085
0.1923	22.32	625	0.5741	36.2046	34.3669
0.198	23.21	650	0.5731	36.1373	34.3669
0.1699	24.11	675	0.5757	36.2719	34.5607
0.1662	25.0	700	0.5768	36.6083	34.9483
0.1559	25.89	725	0.5762	36.8775	35.1421
0.141	26.79	750	0.5801	36.9448	35.2713
0.1318	27.68	775	0.5791	36.8775	35.2067
0.1342	28.57	800	0.5809	37.0794	35.2713
0.1179	29.46	825	0.5829	36.8775	35.0775
0.1111	30.36	850	0.5835	37.2140	35.4005
0.0993	31.25	875	0.5887	37.0794	35.4005
0.0956	32.14	900	0.5900	36.6756	35.0129
0.0886	33.04	925	0.5944	36.7429	35.0775
0.0811	33.93	950	0.5945	36.3392	34.6899
0.0748	34.82	975	0.6010	36.6083	35.0775
0.0662	35.71	1000	0.5991	36.0700	34.5607

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3