formosan-asr-saisiyat / evaluation_results.json
hunterschep's picture
Publish current best Formosan ASR checkpoint for Saisiyat
1579350 verified
Raw
History Blame Contribute Delete
6.35 kB
{
"aggregate": {
"cer_normalized_micro": 0.0792860273317662,
"character_errors": 3980,
"corpora": 5,
"reference_characters": 50198,
"reference_words": 8748,
"utterances": 1189,
"wer_normalized_micro": 0.2293095564700503,
"word_errors": 2006
},
"by_corpus": [
{
"cer_normalized": "0.08096",
"cer_raw": "0.08096",
"char_deletions": "682",
"char_deletions_raw": "682",
"char_insertions": "482",
"char_insertions_raw": "482",
"char_substitutions": "621",
"char_substitutions_raw": "621",
"eval_corpus": "ILRDF",
"eval_language": "saisiyat",
"eval_utterances": "610",
"reference_characters": "22048",
"reference_characters_raw": "22048",
"reference_words": "3766",
"reference_words_raw": "3766",
"run_id": "xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"wer_normalized": "0.21163",
"wer_raw": "0.21163",
"word_deletions": "108",
"word_deletions_raw": "108",
"word_insertions": "77",
"word_insertions_raw": "77",
"word_substitutions": "612",
"word_substitutions_raw": "612"
},
{
"cer_normalized": "0.283092",
"cer_raw": "0.283092",
"char_deletions": "542",
"char_deletions_raw": "542",
"char_insertions": "304",
"char_insertions_raw": "304",
"char_substitutions": "403",
"char_substitutions_raw": "403",
"eval_corpus": "NTU",
"eval_language": "saisiyat",
"eval_utterances": "104",
"reference_characters": "4412",
"reference_characters_raw": "4412",
"reference_words": "877",
"reference_words_raw": "877",
"run_id": "xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"wer_normalized": "0.651083",
"wer_raw": "0.651083",
"word_deletions": "89",
"word_deletions_raw": "89",
"word_insertions": "40",
"word_insertions_raw": "40",
"word_substitutions": "442",
"word_substitutions_raw": "442"
},
{
"cer_normalized": "0.028431",
"cer_raw": "0.028431",
"char_deletions": "18",
"char_deletions_raw": "18",
"char_insertions": "10",
"char_insertions_raw": "10",
"char_substitutions": "30",
"char_substitutions_raw": "30",
"eval_corpus": "ePark1",
"eval_language": "saisiyat",
"eval_utterances": "75",
"reference_characters": "2040",
"reference_characters_raw": "2040",
"reference_words": "343",
"reference_words_raw": "343",
"run_id": "xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"wer_normalized": "0.151603",
"wer_raw": "0.151603",
"word_deletions": "6",
"word_deletions_raw": "6",
"word_insertions": "2",
"word_insertions_raw": "2",
"word_substitutions": "44",
"word_substitutions_raw": "44"
},
{
"cer_normalized": "0.02624",
"cer_raw": "0.02624",
"char_deletions": "77",
"char_deletions_raw": "77",
"char_insertions": "27",
"char_insertions_raw": "27",
"char_substitutions": "24",
"char_substitutions_raw": "24",
"eval_corpus": "ePark2",
"eval_language": "saisiyat",
"eval_utterances": "106",
"reference_characters": "4878",
"reference_characters_raw": "4878",
"reference_words": "824",
"reference_words_raw": "824",
"run_id": "xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"wer_normalized": "0.106796",
"wer_raw": "0.106796",
"word_deletions": "16",
"word_deletions_raw": "16",
"word_insertions": "8",
"word_insertions_raw": "8",
"word_substitutions": "64",
"word_substitutions_raw": "64"
},
{
"cer_normalized": "0.045184",
"cer_raw": "0.045184",
"char_deletions": "371",
"char_deletions_raw": "371",
"char_insertions": "245",
"char_insertions_raw": "245",
"char_substitutions": "144",
"char_substitutions_raw": "144",
"eval_corpus": "ePark3",
"eval_language": "saisiyat",
"eval_utterances": "294",
"reference_characters": "16820",
"reference_characters_raw": "16820",
"reference_words": "2938",
"reference_words_raw": "2938",
"run_id": "xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"wer_normalized": "0.169503",
"wer_raw": "0.169503",
"word_deletions": "82",
"word_deletions_raw": "82",
"word_insertions": "48",
"word_insertions_raw": "48",
"word_substitutions": "368",
"word_substitutions_raw": "368"
}
],
"condition": "language_pooled",
"dataset_version": "dataset_v1",
"iso_639_3": "xsy",
"language": "Saisiyat",
"language_id": "saisiyat",
"model_family": "xlsr53",
"normalization_version": "formosan_safe_v1",
"readiness": {
"actual_train_rows": 9473,
"best_selection_cer": 0.09279681756460974,
"best_selection_wer": 0.2676440207226045,
"best_step": 14210,
"condition": "language_pooled",
"dominant_hypothesis_rate": 0.001682085786375105,
"estimated_effective_epochs": 30.000211126359126,
"failures": 0,
"generated_at": "2026-06-23T08:17:51+00:00",
"intended_train_rows": 9473,
"manifest_dir": "/projects/prudlab/tacl_formosan_asr/experiments/manifests/gate4_xlsr_supervised_matrix/xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"nonempty_hypothesis_rate": 0.9991589571068125,
"prediction_rows": 1189,
"result_dir": "/scratch/scheppat/projects/tacl_formosan_asr/runs_xlsr_final_v2/xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"result_label": "final",
"run_id": "xlsr53_language_pooled_train-saisiyat_eval-saisiyat-all-corpora_dataset_v1_split_v2_formosan_safe_v1_seed13",
"status": "pass",
"steps": 35524,
"test_rows": 1189,
"train_batch_size": 8,
"warnings": 0
},
"seed": 13,
"split_version": "split_v2"
}