add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 58, "</s>": 59}

eval.py

@@ -0,0 +1,128 @@
+#!/usr/bin/env python3
+import argparse
+import re
+from typing import Dict
+
+from datasets import Audio, Dataset, load_dataset, load_metric
+
+from transformers import AutoFeatureExtractor, pipeline
+
+
+def log_results(result: Dataset, args: Dict[str, str]):
+    """DO NOT CHANGE. This function computes and logs the result metrics."""
+
+    log_outputs = args.log_outputs
+    dataset_id = "_".join(args.dataset.split("/") + [args.config, args.split])
+
+    # load metric
+    wer = load_metric("wer")
+    cer = load_metric("cer")
+
+    # compute metrics
+    wer_result = wer.compute(references=result["target"], predictions=result["prediction"])
+    cer_result = cer.compute(references=result["target"], predictions=result["prediction"])
+
+    # print & log results
+    result_str = f"WER: {wer_result}\n" f"CER: {cer_result}"
+    print(result_str)
+
+    with open(f"{dataset_id}_eval_results.txt", "w") as f:
+        f.write(result_str)
+
+    # log all results in text file. Possibly interesting for analysis
+    if log_outputs is not None:
+        pred_file = f"log_{dataset_id}_predictions.txt"
+        target_file = f"log_{dataset_id}_targets.txt"
+
+        with open(pred_file, "w") as p, open(target_file, "w") as t:
+
+            # mapping function to write output
+            def write_to_file(batch, i):
+                p.write(f"{i}" + "\n")
+                p.write(batch["prediction"] + "\n")
+                t.write(f"{i}" + "\n")
+                t.write(batch["target"] + "\n")
+
+            result.map(write_to_file, with_indices=True)
+
+
+def normalize_text(text: str) -> str:
+    """DO ADAPT FOR YOUR USE CASE. this function normalizes the target text."""
+
+    chars_to_ignore_regex = '[,?.!\-\;\:"“%‘”�—’…–]'  # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
+
+    text = re.sub(chars_to_ignore_regex, "", text.lower())
+
+    # In addition, we can normalize the target text, e.g. removing new lines characters etc...
+    # note that order is important here!
+    token_sequences_to_ignore = ["\n\n", "\n", "   ", "  "]
+
+    for t in token_sequences_to_ignore:
+        text = " ".join(text.split(t))
+
+    return text
+
+
+def main(args):
+    # load dataset
+    dataset = load_dataset(args.dataset, args.config, split=args.split, use_auth_token=True)
+
+    # for testing: only process the first two examples as a test
+    dataset = dataset.select(range(10))
+
+    # load processor
+    feature_extractor = AutoFeatureExtractor.from_pretrained(args.model_id)
+    sampling_rate = feature_extractor.sampling_rate
+
+    # resample audio
+    dataset = dataset.cast_column("audio", Audio(sampling_rate=sampling_rate))
+
+    # load eval pipeline
+    asr = pipeline("automatic-speech-recognition", model=args.model_id)
+
+    # map function to decode audio
+    def map_to_pred(batch):
+        prediction = asr(
+            batch["audio"]["array"], chunk_length_s=args.chunk_length_s, stride_length_s=args.stride_length_s
+        )
+
+        batch["prediction"] = prediction["text"]
+        batch["target"] = normalize_text(batch["sentence"])
+        return batch
+
+    # run inference on all examples
+    result = dataset.map(map_to_pred, remove_columns=dataset.column_names)
+
+    # compute and log_results
+    # do not change function below
+    log_results(result, args)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "--model_id", type=str, required=True, help="Model identifier. Should be loadable with 🤗 Transformers"
+    )
+    parser.add_argument(
+        "--dataset",
+        type=str,
+        required=True,
+        help="Dataset name to evaluate the `model_id`. Should be loadable with 🤗 Datasets",
+    )
+    parser.add_argument(
+        "--config", type=str, required=True, help="Config of the dataset. *E.g.* `'en'`  for Common Voice"
+    )
+    parser.add_argument("--split", type=str, required=True, help="Split of the dataset. *E.g.* `'test'`")
+    parser.add_argument(
+        "--chunk_length_s", type=float, default=None, help="Chunk length in seconds. Defaults to 5 seconds."
+    )
+    parser.add_argument(
+        "--stride_length_s", type=float, default=None, help="Stride of the audio chunks. Defaults to 1 second."
+    )
+    parser.add_argument(
+        "--log_outputs", action="store_true", help="If defined, write outputs to log file for analysis."
+    )
+    args = parser.parse_args()
+
+    main(args)

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"'": 1, "،": 2, "؟": 3, "ء": 4, "آ": 5, "ؤ": 6, "ئ": 7, "ا": 8, "ب": 9, "ت": 10, "ث": 11, "ج": 12, "ح": 13, "خ": 14, "د": 15, "ذ": 16, "ر": 17, "ز": 18, "س": 19, "ش": 20, "ص": 21, "ض": 22, "ط": 23, "ظ": 24, "ع": 25, "غ": 26, "ف": 27, "ق": 28, "ل": 29, "م": 30, "ن": 31, "و": 32, "ى": 33, "ي": 34, "َ": 35, "ُ": 36, "ِ": 37, "ّ": 38, "ٔ": 39, "ٰ": 40, "ٹ": 41, "پ": 42, "چ": 43, "ڈ": 44, "ڑ": 45, "ژ": 46, "ک": 47, "گ": 48, "ں": 49, "ھ": 50, "ہ": 51, "ۂ": 52, "ی": 53, "ے": 54, "۔": 55, "|": 0, "[UNK]": 56, "[PAD]": 57}