datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
eval-whisper-large-v3-turbo-medical-terms-2025-20260408-1926
Evaluation Results: whisper-large-v3-turbo
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
openai/whisper-large-v3-turbo
9.37%
3.17%
Source Data
Evaluation Dataset: Trelis/medical-terms-2025
Model Evaluated: openai/whisper-large-v3-turbo
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction
Model prediction
wer
Word… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-large-v3-turbo-medical-terms-2025-20260408-1926.Punjabi-STT-Turbo-40HThis dataset has been partitioned from alvynabranches/punjabi_stt_v1 dataset of 180 hours.
Huge thanks to him for providing this dataset publicly.
Punjabi-STT-Turbo-20HThis dataset has been partitioned from alvynabranches/punjabi_stt_v1 dataset of 180 hours.
Huge thanks to him for providing this dataset publicly.
eval-whisper-large-v3-turbo-eka-hard-20260408-1921
Evaluation Results: whisper-large-v3-turbo
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
openai/whisper-large-v3-turbo
35.09%
21.61%
Source Data
Evaluation Dataset: Trelis/eka-hard
Model Evaluated: openai/whisper-large-v3-turbo
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction
Model prediction
wer
Word Error Rate… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-large-v3-turbo-eka-hard-20260408-1921.synthetic_teacher_largev3_turbowhisper_turboeval-whisper-large-v3-turbo-multimed-hard-20260408-1931
Evaluation Results: whisper-large-v3-turbo
Evaluation results from Whisper model evaluation.
Summary
Model
WER
CER
openai/whisper-large-v3-turbo
9.25%
5.61%
Source Data
Evaluation Dataset: Trelis/multimed-hard
Model Evaluated: openai/whisper-large-v3-turbo
Columns
Column
Description
audio
Audio sample (if available from source dataset)
reference
Ground truth transcription
prediction
Model prediction
wer
Word Error… See the full description on the dataset page: https://huggingface.co/datasets/Trelis/eval-whisper-large-v3-turbo-multimed-hard-20260408-1931.Punjabi-STT-Turbo-16HThis dataset has been partitioned from alvynabranches/punjabi_stt_v1 dataset of 180 hours.
Huge thanks to him for providing this dataset publicly.
