Automatic Speech Recognition
Sherry26
Published
0
Fine-tuning XLSR-Wav2Vec2 for Arabic ASR with ๐ค Transformers
Specifics
- torchaudio, librosa, and jiwer
- Dataset: Common Voice Dataset For Multi-language
- Transformer: XLSR-Wav2Vec2
-These are essential for loading audio files and evaluating the fine-tuned model using the word error rate (WER) metric.
#asr #automaticspeechrecognition #transformer #largelanguagemodels #aiengineer #pytorch