Added eval results and eval commands

README.md

@@ -12,7 +12,21 @@ datasets:
 - common_voice
 model-index:
 - name: wav2vec2-xls-r-300m-lg
-  results: []
+  results:
+  - task: 
+      name: Automatic Speech Recognition 
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 7
+      type: mozilla-foundation/common_voice_7_0
+      args: sv-SE
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 78.89
+       - name: Test CER
+         type: cer
+         value: 15.16
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -66,3 +80,10 @@ The following hyperparameters were used during training:
 - Pytorch 1.10.2+cu102
 - Datasets 1.18.2.dev0
 - Tokenizers 0.11.0
+
+#### Evaluation Commands
+1. To evaluate on `mozilla-foundation/common_voice_7_0` with split `test`
+
+```bash
+python eval.py --model_id samitizerxu/wav2vec2-xls-r-300m-lg --dataset mozilla-foundation/common_voice_7_0 --config lg --split test
+```

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)

log_mozilla-foundation_common_voice_7_0_lg_test_predictions.txt

@@ -0,0 +1,20 @@
+0
+ebintu bizibu okimanyimaamawa omwano oyo yeetuzelwabbaawe kuwasa mutyalamulala.
+1
+tugenze mukkanisa nayo mubwuliza atulangidde okusaba kunnakwe nkuluzikka.
+2
+boolaba omuze eye nga akyattungana okunoonya ssenteomayanti teyateekera teeera bulungi bukaddebwe.
+3
+omunnyo gwaleerwo nga gukaawa nnyo.
+4
+oteekeddwaokutabula obulungi eddagale eryo nga tonnali wa mwaanooyo.
+5
+abakyala bonnaabasatu be nninabakolagga na bulungi eera buyoomu afaayo erimune.
+6
+omulenzi oliya mutuufuokusikira omusajjoono.
+7
+ekikajju kimukubirina ebirimu ssente ndakubina.
+8
+sikatyamanvu uki ekisse nga okukkunga omeraa.
+9
+toombuulira bigambu byamukazioyo okuba nnabekowa.

log_mozilla-foundation_common_voice_7_0_lg_test_targets.txt

@@ -0,0 +1,20 @@
+0
+"ebintu bizibu okimanyi maama w'omwana oyo yeetuze lwa bbaawe kuwasa mukyala mulala?"
+1
+tugenze mu kkanisa naye omubuulizi atulangidde okusaba ku nnaku enkulu zokka.
+2
+"bw'olaba omuzeeyi nga akyattunka n'okunoonya ssente omanya nti teyateekerateekera bulungi bukadde bwe."
+3
+omunnyo gwa leero nga gukaawa nnyo?
+4
+oteekeddwa okutabula obulungi eddagala eryo nga tonnaliwa mwana oyo.
+5
+abakyala bonna abasatu be nnina bakolagana bulungi era buli omu afaayo eri munne.
+6
+omulenzi oli ye mutuufu okusikira omusajja ono.
+7
+ekikajjo kimu ku birime ebirimu ssente ennaku zino.
+8
+"kika ky'amenvu ki ekisinga okukuwoomera?"
+9
+tombuulira bigambo bya mukazi oyo kuba nnabikoowa.

mozilla-foundation_common_voice_7_0_lg_test_eval_results.txt

@@ -0,0 +1,2 @@
+WER: 0.7888888888888889
+CER: 0.1515625