wav2vec2-large-xlsr-mvc-swahili

This model is a finetuned version of facebook/wav2vec2-large-xlsr-53. There was an issue with vocab, seems like there are special characters included and they were not considered during training You could try from transformers import AutoProcessor, AutoModelForCTC repo_name = "eddiegulay/wav2vec2-large-xlsr-mvc-swahili" processor = AutoProcessor.from_pretrained(repo_name) model = AutoModelForCTC.from_pretrained(repo_name) model = model.to("cuda") def transcribe(audio_path): audio_input, sample_rate = torchaudio.load(audio_path) target_sample_rate = 16000 audio_input = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=target_sample_rate)(audio_input) input_dict = processor(audio_input[0], return_tensors="pt", padding=True, sampling_rate=16000) logits = model(input_dict.input_values.to("cuda")).logits pred_ids = torch.argmax(logits, dim=-1)[0] transcription = processor.decode(pred_ids) return transcription transcript = transcribe('your_audio.mp3')