|
--- |
|
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 |
|
--- |
|
this model trained on validation segment of data for one epoch with 0.05 loss and tested on test segment of data with 0.07 loss and WER: 1.636687802644541 |
|
|
|
how to use the model in colab: |
|
|
|
# Install required packages |
|
!pip install torch torchaudio transformers pydub google-colab |
|
|
|
import torch |
|
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline |
|
from pydub import AudioSegment |
|
import os |
|
from google.colab import files |
|
|
|
# Load the model and processor |
|
model_id = "hackergeek98/tinyyyy_whisper" |
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
|
model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id).to(device) |
|
processor = AutoProcessor.from_pretrained(model_id) |
|
|
|
# Create pipeline |
|
whisper_pipe = pipeline( |
|
"automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, device=0 if torch.cuda.is_available() else -1 |
|
) |
|
|
|
# Convert audio to WAV format |
|
def convert_to_wav(audio_path): |
|
audio = AudioSegment.from_file(audio_path) |
|
wav_path = "converted_audio.wav" |
|
audio.export(wav_path, format="wav") |
|
return wav_path |
|
|
|
# Split long audio into chunks |
|
def split_audio(audio_path, chunk_length_ms=30000): # Default: 30 sec per chunk |
|
audio = AudioSegment.from_wav(audio_path) |
|
chunks = [audio[i:i+chunk_length_ms] for i in range(0, len(audio), chunk_length_ms)] |
|
chunk_paths = [] |
|
|
|
for i, chunk in enumerate(chunks): |
|
chunk_path = f"chunk_{i}.wav" |
|
chunk.export(chunk_path, format="wav") |
|
chunk_paths.append(chunk_path) |
|
|
|
return chunk_paths |
|
|
|
# Transcribe a long audio file |
|
def transcribe_long_audio(audio_path): |
|
wav_path = convert_to_wav(audio_path) |
|
chunk_paths = split_audio(wav_path) |
|
transcription = "" |
|
|
|
for chunk in chunk_paths: |
|
result = whisper_pipe(chunk) |
|
transcription += result["text"] + "\n" |
|
os.remove(chunk) # Remove processed chunk |
|
|
|
os.remove(wav_path) # Cleanup original file |
|
|
|
# Save transcription to a text file |
|
text_path = "transcription.txt" |
|
with open(text_path, "w") as f: |
|
f.write(transcription) |
|
|
|
return text_path |
|
|
|
# Upload and process audio in Colab |
|
uploaded = files.upload() |
|
audio_file = list(uploaded.keys())[0] |
|
transcription_file = transcribe_long_audio(audio_file) |
|
|
|
# Download the transcription file |
|
files.download(transcription_file) |
|
|
|
|
|
|
|
|
|
|
