import gradio as gr import pandas as pd from css_html_js import custom_css TITLE = """

🇲🇾 Malaysian Speech-to-Text Leaderboard

""" INTRODUCTION_TEXT = """ 📐 The 🇲🇾 Malaysian Speech-to-Text Leaderboard aims to track, rank and evaluate Malaysian Speech-to-Text models. All notebooks at https://github.com/mesolitica/malaysian-stt-benchmarks ## Dataset 📈 We evaluate models based on 3 datasets, 1. Malaya-Speech test set, Malay language, https://huggingface.co/datasets/huseinzol05/malaya-speech-stt-test-set/tree/main/malaya-speech 2. Fleurs MS-MY test set, Malay language, https://huggingface.co/datasets/huseinzol05/malaya-speech-stt-test-set/tree/main/fleurs-ms-my 3. IMDA TTS first 700 audio files, English language but with Manglish slang, https://huggingface.co/datasets/mesolitica/IMDA-TTS ## Heavy postprocess test set 1. We filtered test set that contain numbers because malaya-speech transducer trained on normalized numbers. 2. We lower case because malaya-speech transducer trained on lower case. 3. We removed punctuation because malaya-speech transducer trained without punctuation. """ open_source = [ { 'model': 'goodtape.io', 'model size FP16 (MB)': None, 'Malaya-Speech test CER': 0.09504487340205486, 'Malaya-Speech test WER': 0.1691902868373457, 'Fleurs MY-MS CER': 0.03643102801583697, 'Fleurs MY-MS WER': 0.08672758155453257, }, { 'model': 'openai/whisper-large-v3', 'model size FP16 (MB)': 3090, 'Malaya-Speech test CER': 0.0349251317825172, 'Malaya-Speech test WER': 0.1032828282828283, 'Fleurs MY-MS CER': 0.026055551396846878, 'Fleurs MY-MS WER': 0.07652049926522007, 'IMDA TTS CER': 0.016648493852990828, 'IMDA TTS WER': 0.0386282289139432, }, { 'model': 'openai/whisper-medium', 'model size FP16 (MB)': 1530, 'Malaya-Speech test CER': 0.05064920144820262, 'Malaya-Speech test WER': 0.17534205321090568, 'Fleurs MY-MS CER': 0.04366882208520179, 'Fleurs MY-MS WER': 0.13546055192128273, 'IMDA TTS CER': 0.02065587879424904, 'IMDA TTS WER': 0.047277690563404855, }, { 'model': 'openai/whisper-small', 'model size FP16 (MB)': 483.5, 'Malaya-Speech test CER': 0.07485209857268262, 'Malaya-Speech test WER': 0.25748516055893106, 'Fleurs MY-MS CER': 0.06781078047622793, 'Fleurs MY-MS WER': 0.21953142859857497, 'IMDA TTS CER': 0.024812471688517194, 'IMDA TTS WER': 0.058901277294134434, }, { 'model': 'openai/whisper-base', 'model size FP16 (MB)': 145, 'Malaya-Speech test CER': 0.3574879236610538, 'Malaya-Speech test WER': 0.8303456599563157, 'Fleurs MY-MS CER': 0.1319124653794061, 'Fleurs MY-MS WER': 0.40499286081235003, 'IMDA TTS CER': 0.03914533450681607, 'IMDA TTS WER': 0.08951682444539587, }, { 'model': 'openai/whisper-tiny', 'model size FP16 (MB)': 75.5, 'Malaya-Speech test CER': 0.26941094281472105, 'Malaya-Speech test WER': 0.7414099751189915, 'Fleurs MY-MS CER': 0.38749733168917505, 'Fleurs MY-MS WER': 0.812253445128297, 'IMDA TTS CER': 0.048805770734828904, 'IMDA TTS WER': 0.11150629529200957, }, { 'model': 'mesolitica/malaysian-whisper-medium', 'model size FP16 (MB)': 1530, 'Malaya-Speech test CER': 0.05622483776367814, 'Malaya-Speech test WER': 0.14406629724252673, 'Fleurs MY-MS CER': 0.025543266604368554, 'Fleurs MY-MS WER': 0.07940219915492629, 'IMDA TTS CER': 0.01971214262944062, 'IMDA TTS WER': 0.047223078508792794, }, { 'model': 'mesolitica/malaysian-whisper-small', 'model size FP16 (MB)': 483.5, 'Malaya-Speech test CER': 0.049162419174983304, 'Malaya-Speech test WER': 0.15926901346983313, 'Fleurs MY-MS CER': 0.035517572531147, 'Fleurs MY-MS WER': 0.10938718963023729, 'IMDA TTS CER': 0.024228721439634855, 'IMDA TTS WER': 0.05546294182008469, }, { 'model': 'mesolitica/malaysian-whisper-base', 'model size FP16 (MB)': 145, 'Malaya-Speech test CER': 0.07242006488452603, 'Malaya-Speech test WER': 0.22081683495617924, 'Fleurs MY-MS CER': 0.06639564802362424, 'Fleurs MY-MS WER': 0.19675812232021192, 'IMDA TTS CER': 0.03982418421412676, 'IMDA TTS WER': 0.08917690642690643, }, { 'model': 'mesolitica/malaysian-whisper-tiny', 'model size FP16 (MB)': 75.5, 'Malaya-Speech test CER': 0.09423990117534763, 'Malaya-Speech test WER': 0.295029492365558, 'Fleurs MY-MS CER': 0.13390519685940314, 'Fleurs MY-MS WER': 0.3461808122686204, 'IMDA TTS CER': 0.07957313474501154, 'IMDA TTS WER': 0.1421708648494363, }, { 'model': 'mesolitica/conformer-large-malay-whisper', 'model size FP16 (MB)': 206.5, 'Malaya-Speech test CER': 0.025933167255719317, 'Malaya-Speech test WER': 0.0912131356803488, 'Fleurs MY-MS CER': 0.02548791948171514, 'Fleurs MY-MS WER': 0.08376713097429746, }, { 'model': 'mesolitica/conformer-medium-malay-whisper', 'model size FP16 (MB)': 121.5, 'Malaya-Speech test CER': 0.024955598713609053, 'Malaya-Speech test WER': 0.09315638444736804, 'Fleurs MY-MS CER': 0.029205645523910067, 'Fleurs MY-MS WER': 0.09253131557833799, }, { 'model': 'mesolitica/conformer-medium-mixed', 'model size FP16 (MB)': 121.5, 'Malaya-Speech test CER': 0.034618711056551774, 'Malaya-Speech test WER': 0.11179440626161938, 'Fleurs MY-MS CER': 0.032894184549728075, 'Fleurs MY-MS WER': 0.1026977414887425, }, { 'model': 'mesolitica/conformer-tiny-ctc + mesolitica/kenlm-pseudolabel-whisper-large-v3', 'model size FP16 (MB)': 7.9, 'Malaya-Speech test CER': 0.0612581761581601, 'Malaya-Speech test WER': 0.21302693966628394, 'Fleurs MY-MS CER': 0.07573301800412188, 'Fleurs MY-MS WER': 0.2527434609577528, }, { 'model': 'mesolitica/conformer-12M-ctc + mesolitica/kenlm-pseudolabel-whisper-large-v3', 'model size FP16 (MB)': 24.2, 'Malaya-Speech test CER': 0.06941749946814912, 'Malaya-Speech test WER': 0.22261096523391607, 'Fleurs MY-MS CER': 0.07657934690019219, 'Fleurs MY-MS WER': 0.263075623142674, }, ] data = pd.DataFrame(open_source) demo = gr.Blocks(css=custom_css) with demo: gr.HTML(TITLE) gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text") gr.DataFrame(data) demo.launch()