| | --- |
| | library_name: transformers |
| | language: |
| | - en |
| | pipeline_tag: automatic-speech-recognition |
| | tags: |
| | - audio |
| | - asr |
| | - whisper |
| | --- |
| | |
| | # Model Card for Arsalan07/whisper-api |
| |
|
| | This is a fine-tuned [OpenAI Whisper Small](https://huggingface.co/openai/whisper-small) model |
| | for **automatic speech recognition (ASR)** in English. |
| |
|
| | It was fine-tuned with 🤗 `transformers` and `datasets` on custom audio/transcript data. |
| |
|
| |
|
| | ## Model Details |
| |
|
| | - **Base model:** `openai/whisper-small` |
| | - **Task:** Automatic Speech Recognition (speech → text) |
| | - **Language:** English (`en`) |
| | - **Files included:** |
| | - `model.safetensors` (weights ~967MB) |
| | - `config.json`, `generation_config.json` |
| | - `preprocessor_config.json` |
| | - tokenizer-related files |
| |
|
| | --- |
| |
|
| | ## How to Use |
| |
|
| | ### In Python (pipeline) |
| | ```python |
| | # Authenticate with Hugging Face |
| | |
| | from huggingface_hub import login |
| | login(token="") |
| | |
| | from transformers import pipeline |
| | |
| | # Load fine-tuned Whisper model with authentication |
| | |
| | pipe = pipeline( |
| | "automatic-speech-recognition", |
| | model="Arsalan07/whisper-api", |
| | ) |
| | |
| | # Test on an audio file |
| | |
| | print(pipe("test.mp3")["text"]) |
| | |
| | ``` |
