|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- mozilla-foundation/common_voice_13_0 |
|
- google/fleurs |
|
language: |
|
- ig |
|
--- |
|
facebook/wav2vec2-xls-r-300m fine-tuned on google/fleurs and mozilla-foundation/common_voice_13_0 for Igbo language. |
|
|
|
WER: 0.51 |
|
|
|
|
|
Code for running: |
|
``` |
|
from huggingsound import SpeechRecognitionModel |
|
|
|
model = SpeechRecognitionModel("AstralZander/igbo_ASR") |
|
audio_paths = [audio_path] # List with paths to audio |
|
transcriptions = model.transcribe(audio_paths) |
|
|
|
transcriptions # List of transcriptions, timestamps and probabilities |
|
transcriptions[ind_audio]['transcription'] # Transcription of audio with the ind_audio index from the audio_paths list |
|
``` |
