datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
sada_preprocessed_whisper_smallwhisper-small-ko-meeting-datawhisper_transcriptions.reazonspeech.smallatcosim_dataset_for_finetune_whisper_smallwhisper-small-hindi
Dataset Card for "whisper-small-hindi"
More Information needed
arc_whisper_medium_transcriptions.reazonspeech.small
Dataset Card for "arc_whisper_medium_transcriptions.reazonspeech.small"
More Information needed
arc_whisper_transcriptions.reazonspeech.small
Dataset Card for "arc_whisper_transcriptions.reazonspeech.small"
More Information needed
eval-whisper-small-english-eka-hard-20260408-1925
Evaluation Results: whisper-small-english
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
leduckhai/MultiMed-ST/asr/whisper-small-english
49.12%
35.11%
Source Data
Evaluation Dataset: Trelis/eka-hard
Model Evaluated: leduckhai/MultiMed-ST/asr/whisper-small-english
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-english-eka-hard-20260408-1925.whisper_transcriptions.reazonspeech.small.wer_10.0eval-whisper-small-eka-hard-20260408-1924
Evaluation Results: whisper-small
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
openai/whisper-small
520.05%
278.24%
Source Data
Evaluation Dataset: Trelis/eka-hard
Model Evaluated: openai/whisper-small
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction
Model prediction
wer
Word Error Rate for this sample
cer… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-eka-hard-20260408-1924.arc_whisper_transcriptions.reazonspeech.small.wer_10.0
Dataset Card for "arc_whisper_transcriptions.reazonspeech.small.wer_10.0"
More Information needed
arc_whisper_medium_transcriptions.reazonspeech.small.wer_10.0
Dataset Card for "arc_whisper_medium_transcriptions.reazonspeech.small.wer_10.0"
More Information needed
whisper_smallWhisperSmallTestmp3
Dataset Card for "WhisperSmallTestmp3"
More Information needed
whisper.kotoba.small.wer_10.0
Dataset Card for "whisper.kotoba.small.wer_10.0"
More Information needed
eval-whisper-small-english-multimed-hard-20260408-1935
Evaluation Results: whisper-small-english
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
leduckhai/MultiMed-ST/asr/whisper-small-english
11.46%
7.46%
Source Data
Evaluation Dataset: Trelis/multimed-hard
Model Evaluated: leduckhai/MultiMed-ST/asr/whisper-small-english
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-english-multimed-hard-20260408-1935.eval-whisper-small-medical-terms-2025-20260408-1929
Evaluation Results: whisper-small
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
openai/whisper-small
12.95%
4.24%
Source Data
Evaluation Dataset: Trelis/medical-terms-2025
Model Evaluated: openai/whisper-small
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction
Model prediction
wer
Word Error Rate for this sample… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-medical-terms-2025-20260408-1929.eval-whisper-small-english-medical-terms-2025-20260408-1931
Evaluation Results: whisper-small-english
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
leduckhai/MultiMed-ST/asr/whisper-small-english
13.44%
4.94%
Source Data
Evaluation Dataset: Trelis/medical-terms-2025
Model Evaluated: leduckhai/MultiMed-ST/asr/whisper-small-english
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-english-medical-terms-2025-20260408-1931.WhisperSmallTest200002
Dataset Card for "WhisperSmallTest200002"
More Information needed
whisper-small-hindiwhisper-small-hindi
Dataset Card for "whisper-small-hindi"
More Information needed
whisper-small-hindi
Dataset Card for "whisper-small-hindi"
More Information needed
eval-whisper-small-pilotgpt-unified-all-data-lowercase-new-rewritten-20260223-2259
Training Evaluation: whisper-small-pilotgpt-unified-all-data-lowercase-new-rewritten
Evaluation results comparing base model vs fine-tuned model.
Summary
Model
WER
openai/whisper-small (base)
46.81%
Trelis/whisper-small-pilotgpt-unified-all-data-lowercase-new-rewritten (fine-tuned)
34.22%
Improvement: 12.59% WER reduction (lower is better)
Source Data
Evaluation Dataset: Trelis/pilotgpt-test-0.5s-rewritten
Base Model: openai/whisper-small… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-pilotgpt-unified-all-data-lowercase-new-rewritten-20260223-2259.eval-whisper-small-multimed-hard-20260408-1933
Evaluation Results: whisper-small
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
openai/whisper-small
13.31%
7.49%
Source Data
Evaluation Dataset: Trelis/multimed-hard
Model Evaluated: openai/whisper-small
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction
Model prediction
wer
Word Error Rate for this sample
cer… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-multimed-hard-20260408-1933.eval-whisper-small-pilotgpt-unified-all-data-lowercase-data-prep-6772-20260219-1448
Training Evaluation: whisper-small-pilotgpt-unified-all-data-lowercase-data-prep-6772
Evaluation results comparing base model vs fine-tuned model.
Summary
Model
WER
openai/whisper-small (base)
53.69%
Trelis/whisper-small-pilotgpt-unified-all-data-lowercase-data-prep-6772 (fine-tuned)
27.54%
Improvement: 26.15% WER reduction (lower is better)
Source Data
Evaluation Dataset: Trelis/pilotgpt-test-0.5s
Base Model: openai/whisper-small… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-pilotgpt-unified-all-data-lowercase-data-prep-6772-20260219-1448.eval-whisper-small-pilotgpt-unified-all-raw-nopack-0.5s-clean-7283-20260227-2013
Training Evaluation: whisper-small-pilotgpt-unified-all-raw-nopack-0.5s-clean-7283
Evaluation results comparing base model vs fine-tuned model.
Summary
Model
WER
openai/whisper-small (base)
53.69%
Trelis/whisper-small-pilotgpt-unified-all-raw-nopack-0.5s-clean-7283 (fine-tuned)
32.92%
Improvement: 20.77% WER reduction (lower is better)
Source Data
Evaluation Dataset: Trelis/pilotgpt-test-0.5s
Base Model: openai/whisper-small
Fine-tuned… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-small-pilotgpt-unified-all-raw-nopack-0.5s-clean-7283-20260227-2013.
