|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- mozilla-foundation/common_voice_11_0 |
|
|
language: |
|
|
- fa |
|
|
metrics: |
|
|
- wer |
|
|
base_model: |
|
|
- openai/whisper-tiny |
|
|
pipeline_tag: automatic-speech-recognition |
|
|
library_name: transformers |
|
|
--- |
|
|
how to use the model in colab: |
|
|
|
|
|
#start |
|
|
pip install torch torchaudio transformers librosa gradio |
|
|
from transformers import WhisperProcessor, WhisperForConditionalGeneration |
|
|
import torch |
|
|
|
|
|
#Load your fine-tuned Whisper model and processor |
|
|
model_name = "hackergeek98/tinyyyy_whisper" |
|
|
processor = WhisperProcessor.from_pretrained(model_name) |
|
|
model = WhisperForConditionalGeneration.from_pretrained(model_name) |
|
|
|
|
|
#Force the model to transcribe in Persian |
|
|
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="fa", task="transcribe") |
|
|
|
|
|
#Move model to GPU if available |
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
model.to(device) |
|
|
import librosa |
|
|
|
|
|
def transcribe_audio(audio_file): |
|
|
# Load audio file using librosa (supports multiple formats) |
|
|
audio_data, sampling_rate = librosa.load(audio_file, sr=16000) # Resample to 16kHz |
|
|
|
|
|
# Preprocess the audio |
|
|
inputs = processor(audio_data, sampling_rate=sampling_rate, return_tensors="pt").input_features.to(device) |
|
|
|
|
|
# Generate transcription |
|
|
with torch.no_grad(): |
|
|
predicted_ids = model.generate(inputs) |
|
|
|
|
|
# Decode the transcription |
|
|
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0] |
|
|
return transcription |
|
|
from google.colab import files |
|
|
|
|
|
#Upload an audio file |
|
|
uploaded = files.upload() |
|
|
audio_file = list(uploaded.keys())[0] |
|
|
|
|
|
#Transcribe the audio |
|
|
transcription = transcribe_audio(audio_file) |
|
|
print("Transcription:", transcription) |
|
|
|
