Spaces:
Runtime error
Runtime error
| import torch | |
| import gradio as gr | |
| from transformers import pipeline | |
| model_id = "Sandiago21/whisper-large-v2-spanish" # update with your model id | |
| pipe = pipeline("automatic-speech-recognition", model=model_id) | |
| title = "Automatic Speech Recognition (ASR)" | |
| description = """ | |
| Demo for automatic speech recognition in Spanish. Demo uses [Sandiago21/whisper-large-v2-spanish](https://huggingface.co/Sandiago21/whisper-large-v2-spanish) checkpoint, which is based on OpenAI's | |
| [Whisper](https://huggingface.co/openai/whisper-large-v2) model and is fine-tuned in Spanish Audio dataset | |
|  | |
| """ | |
| def transcribe_speech(filepath): | |
| output = pipe( | |
| filepath, | |
| max_new_tokens=256, | |
| generate_kwargs={ | |
| "task": "transcribe", | |
| "language": "spanish", | |
| }, # update with the language you've fine-tuned on | |
| chunk_length_s=30, | |
| batch_size=8, | |
| ) | |
| return output["text"] | |
| demo = gr.Blocks() | |
| mic_transcribe = gr.Interface( | |
| fn=transcribe_speech, | |
| inputs=gr.Audio(source="microphone", type="filepath"), | |
| outputs=gr.outputs.Textbox(), | |
| tilte=title, | |
| description=description, | |
| ) | |
| file_transcribe = gr.Interface( | |
| fn=transcribe_speech, | |
| inputs=gr.Audio(source="upload", type="filepath"), | |
| outputs=gr.outputs.Textbox(), | |
| examples=[["./example.wav"]], | |
| tilte=title, | |
| description=description, | |
| ) | |
| with demo: | |
| gr.TabbedInterface( | |
| [mic_transcribe, file_transcribe], | |
| ["Transcribe Microphone", "Transcribe Audio File"], | |
| ), | |
| demo.launch() | |