| { |
| "repo_id": "faeea/custom-gopt-252-eval", |
| "description": "Bundle of the v6 ASR-confidence Streaming GOPT checkpoint plus the Whisper and Charsiu models required by the local evaluation pipeline.", |
| "artifacts": [ |
| { |
| "path": "streaming_gopt_best/best_audio_model.pth", |
| "type": "streaming_gopt_weights", |
| "purpose": "Pronunciation scoring model selected by validation phone MSE." |
| }, |
| { |
| "path": "streaming_gopt_best/config.json", |
| "type": "streaming_gopt_config", |
| "purpose": "Network shape and training arguments used to restore the v6 ASR-confidence model." |
| }, |
| { |
| "path": "streaming_gopt_best/result.csv", |
| "type": "training_metrics", |
| "purpose": "Per-epoch train/validation metrics." |
| }, |
| { |
| "path": "streaming_gopt_best/test_metrics.json", |
| "type": "test_metrics", |
| "purpose": "Held-out test metrics for the best validation checkpoint." |
| }, |
| { |
| "path": "streaming_gopt_best/inference_assets.json", |
| "type": "inference_metadata", |
| "purpose": "Normalization stats, feature dimension, and phone-id mapping required for one-audio local inference." |
| }, |
| { |
| "path": "whisper_best_model", |
| "type": "transformers_whisper_model", |
| "purpose": "ASR model used to build ASR-driven GOPT chunks." |
| }, |
| { |
| "path": "charsiu_en_w2v2_tiny_fc_10ms", |
| "type": "charsiu_aligner_model", |
| "purpose": "Frame-level phone alignment model used by preprocessing and inference." |
| }, |
| { |
| "path": "examples/infer_one_audio.py", |
| "type": "example_script", |
| "purpose": "Minimal one-audio local inference script that prints utterance-level scores." |
| }, |
| { |
| "path": "examples/eval_streaming_gopt_test.py", |
| "type": "example_script", |
| "purpose": "Minimal evaluation script for val/test split using the bundled best GOPT checkpoint." |
| } |
| ], |
| "model_outputs": { |
| "utterance": [ |
| "accuracy", |
| "completeness", |
| "fluency", |
| "prosodic", |
| "total" |
| ], |
| "phone": [ |
| "phone pronunciation score" |
| ], |
| "word": [ |
| "accuracy", |
| "stress", |
| "total", |
| "asr_accuracy" |
| ], |
| "word_asr_accuracy_note": "The word-level ASR accuracy score can be used as an auxiliary indicator of whether the word was read correctly." |
| }, |
| "best_validation_summary": { |
| "selection_metric": "phone_val_mse", |
| "best_epoch": 11, |
| "phone_val_mse": 0.04760764539241791, |
| "phone_val_pcc": 0.34831968338670993, |
| "utt_val_pcc_total": 0.661865583803676, |
| "word_val_pcc_total": 0.3418123225833971, |
| "word_val_pcc_asr_accuracy": 0.3633849619530143 |
| }, |
| "test_summary": { |
| "phone_test_mse": 0.04919730871915817, |
| "phone_test_pcc": 0.3975705055993251, |
| "utt_test_pcc": [ |
| 0.651909193610124, |
| 0.012690043750859805, |
| 0.7249977587357453, |
| 0.7332794084754206, |
| 0.681940037784353 |
| ], |
| "word_test_pcc": [ |
| 0.4047142491023989, |
| -0.0039119825110344765, |
| 0.4122583381095728, |
| 0.41746734262039764 |
| ], |
| "word_score_names": [ |
| "accuracy", |
| "stress", |
| "total", |
| "asr_accuracy" |
| ] |
| }, |
| "code_dependencies": { |
| "custom_gopt_repo": "https://github.com/hf49w/custom-gopt.git", |
| "charsiu_repo": "https://github.com/lingjzhu/charsiu", |
| "charsiu_repo_commit": "13a69f2a22ca0c0962b75cc693399b0ae23a12c9" |
| } |
| } |
|
|
