| language: | |
| - km | |
| license: apache-2.0 | |
| library_name: transformers | |
| tags: | |
| - hf-asr-leaderboard | |
| - generated_from_trainer | |
| datasets: | |
| - openslr | |
| - google/fleurs | |
| - seanghay/km-speech-corpus | |
| metrics: | |
| - wer | |
| pipeline_tag: automatic-speech-recognition | |
| base_model: openai/whisper-small | |
| model-index: | |
| - name: Whisper Small Khmer Spaced - Seanghay Yath | |
| results: | |
| - task: | |
| type: automatic-speech-recognition | |
| name: Automatic Speech Recognition | |
| dataset: | |
| name: Google FLEURS | |
| type: google/fleurs | |
| config: km_kh | |
| split: test | |
| metrics: | |
| - type: wer | |
| value: 0.6165 | |
| name: Wer | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # whisper-small-khmer-v2 | |
| This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the `openslr`, `google/fleurs` and `km-speech-corpus` dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.26 | |
| - Wer: 0.6165 | |
| ## Model description | |
| This model is fine-tuned with Google FLEURS, OpenSLR (SLR42) and km-speech-corpus dataset. | |
| ```python | |
| from transformers import pipeline | |
| pipe = pipeline( | |
| task="automatic-speech-recognition", | |
| model="seanghay/whisper-small-khmer-v2", | |
| ) | |
| result = pipe("audio.wav", | |
| generate_kwargs={ | |
| "language":"<|km|>", | |
| "task":"transcribe"}, | |
| batch_size=16 | |
| ) | |
| print(result["text"]) | |
| ``` |