import os import wikipedia os.system("pip install git+https://github.com/openai/whisper.git") import gradio as gr import whisper import jiwer from share_btn import community_icon_html, loading_icon_html, share_js model = whisper.load_model("small") wikipedia.set_lang("en") passage = wikipedia.summary("pirate code", sentences=2) def inference(audio): audio = whisper.load_audio(audio) audio = whisper.pad_or_trim(audio) audio_length = audio.shape[-1]/16000 mel = whisper.log_mel_spectrogram(audio).to(model.device) _, probs = model.detect_language(mel) options = whisper.DecodingOptions(fp16 = False) result = whisper.decode(model, mel, options) transformation = jiwer.Compose([ jiwer.ToLowerCase(), jiwer.RemoveWhiteSpace(replace_by_space=True), jiwer.RemoveMultipleSpaces(), jiwer.ReduceToListOfListOfWords(word_delimiter=" ") ]) error = jiwer.wer( passage, result.text, truth_transform=transformation, hypothesis_transform=transformation ) # error = jiwer.wer(passage, result.text) print(f"WER is {error * len(result.text.split())}") print(result.text) print(passage) return f"For a {audio_length} second audio, WER is {error * len(result.text.split())} \n\n{result.text} resulting in a final time of {audio_length + error * len(result.text.split())}", gr.update(visible=True), gr.update(visible=True), gr.update(visible=True) css = """ .gradio-container { font-family: 'IBM Plex Sans', sans-serif; } .gr-button { color: white; border-color: black; background: black; } input[type='range'] { accent-color: black; } .dark input[type='range'] { accent-color: #dfdfdf; } .container { max-width: 730px; margin: auto; padding-top: 1.5rem; } .details:hover { text-decoration: underline; } .gr-button { white-space: nowrap; } .gr-button:focus { border-color: rgb(147 197 253 / var(--tw-border-opacity)); outline: none; box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); --tw-border-opacity: 1; --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); --tw-ring-opacity: .5; } .footer { margin-bottom: 45px; margin-top: 35px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } .prompt h4{ margin: 1.25em 0 .25em 0; font-weight: bold; font-size: 115%; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; margin-top: 1.5rem !important; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important; } #share-btn * { all: unset; } """ block = gr.Blocks(css=css) with block: gr.HTML( """
The point of the game is to say the given text as fast as possible without errors. Each error adds a one second penaly to the final time and is measured by the WER metric multiplied by text length. The STT is powered by Whisper, a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification. This demo cuts audio after around 30 secs.