| 1 | --- |
| 2 | language: mt |
| 3 | datasets: |
| 4 | - common_voice |
| 5 | tags: |
| 6 | - audio |
| 7 | - automatic-speech-recognition |
| 8 | - speech |
| 9 | - xlsr-fine-tuning-week |
| 10 | license: apache-2.0 |
| 11 | model-index: |
| 12 | - name: XLSR Wav2Vec2 Maltese by Akash PB |
| 13 | results: |
| 14 | - task: |
| 15 | name: Speech Recognition |
| 16 | type: automatic-speech-recognition |
| 17 | dataset: |
| 18 | name: Common Voice mt |
| 19 | type: common_voice |
| 20 | args: {lang_id} |
| 21 | metrics: |
| 22 | - name: Test WER |
| 23 | type: wer |
| 24 | value: 29.42 |
| 25 | --- |
| 26 | # Wav2Vec2-Large-XLSR-53-Maltese |
| 27 | Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Maltese using the [Common Voice](https://huggingface.co/datasets/common_voice) |
| 28 | When using this model, make sure that your speech input is sampled at 16kHz. |
| 29 | ## Usage |
| 30 | The model can be used directly (without a language model) as follows: |
| 31 | ```python |
| 32 | import torchaudio |
| 33 | from datasets import load_dataset, load_metric |
| 34 | from transformers import ( |
| 35 | Wav2Vec2ForCTC, |
| 36 | Wav2Vec2Processor, |
| 37 | ) |
| 38 | import torch |
| 39 | import re |
| 40 | import sys |
| 41 | |
| 42 | model_name = "Akashpb13/xlsr_maltese_wav2vec2" |
| 43 | device = "cuda" |
| 44 | chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\)\\(\\*)]' |
| 45 | |
| 46 | model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device) |
| 47 | processor = Wav2Vec2Processor.from_pretrained(model_name) |
| 48 | |
| 49 | ds = load_dataset("common_voice", "mt", split="test", data_dir="./cv-corpus-6.1-2020-12-11") |
| 50 | |
| 51 | resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000) |
| 52 | |
| 53 | def map_to_array(batch): |
| 54 | speech, _ = torchaudio.load(batch["path"]) |
| 55 | batch["speech"] = resampler.forward(speech.squeeze(0)).numpy() |
| 56 | batch["sampling_rate"] = resampler.new_freq |
| 57 | batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " " |
| 58 | return batch |
| 59 | |
| 60 | ds = ds.map(map_to_array) |
| 61 | |
| 62 | def map_to_pred(batch): |
| 63 | features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt") |
| 64 | input_values = features.input_values.to(device) |
| 65 | attention_mask = features.attention_mask.to(device) |
| 66 | with torch.no_grad(): |
| 67 | logits = model(input_values, attention_mask=attention_mask).logits |
| 68 | pred_ids = torch.argmax(logits, dim=-1) |
| 69 | batch["predicted"] = processor.batch_decode(pred_ids) |
| 70 | batch["target"] = batch["sentence"] |
| 71 | return batch |
| 72 | |
| 73 | result = ds.map(map_to_pred, batched=True, batch_size=1, remove_columns=list(ds.features.keys())) |
| 74 | |
| 75 | wer = load_metric("wer") |
| 76 | print(wer.compute(predictions=result["predicted"], references=result["target"])) |
| 77 | |
| 78 | ``` |
| 79 | **Test Result**: 29.42 % |
| 80 |