Panhapich
/

pre-trained_whisper_wavLM

Automatic Speech Recognition

Model card Files Files and versions

Panhapich commited on Jul 3

Commit

b998aaa

·

verified ·

1 Parent(s): 554ace1

Create phase1_manifest.json

Files changed (1) hide show

phase1_manifest.json +124 -0

phase1_manifest.json ADDED Viewed

	@@ -0,0 +1,124 @@

+{
+  "best_backbone_key": "whisper-base",
+  "best_backbone_id": "openai/whisper-base",
+  "checkpoint_path": "./whisper-base_best.pt",
+  "hidden_size": 512,
+  "phase1_results": {
+    "wavlm-base": 0.603107857566085,
+    "wav2vec2-base": 0.7835776677688794,
+    "whisper-base": 0.5663143408704295
+  },
+  "vocab": [
+    "[BLANK]",
+    "[PAD]",
+    "[MASK]",
+    "[UNK]",
+    "ក",
+    "ខ",
+    "គ",
+    "ឃ",
+    "ង",
+    "ច",
+    "ឆ",
+    "ជ",
+    "ឈ",
+    "ញ",
+    "ដ",
+    "ឋ",
+    "ឌ",
+    "ឍ",
+    "ណ",
+    "ត",
+    "ថ",
+    "ទ",
+    "ធ",
+    "ន",
+    "ប",
+    "ផ",
+    "ព",
+    "ភ",
+    "ម",
+    "យ",
+    "រ",
+    "ល",
+    "វ",
+    "ឝ",
+    "ឞ",
+    "ស",
+    "ហ",
+    "ឡ",
+    "អ",
+    "ឥ",
+    "ឦ",
+    "ឧ",
+    "ឨ",
+    "ឩ",
+    "ឪ",
+    "ឫ",
+    "ឬ",
+    "ឭ",
+    "ឮ",
+    "ឯ",
+    "ឰ",
+    "ឱ",
+    "ឲ",
+    "ឳ",
+    "ា",
+    "ិ",
+    "ី",
+    "ឹ",
+    "ឺ",
+    "ុ",
+    "ូ",
+    "ួ",
+    "ើ",
+    "ឿ",
+    "ៀ",
+    "េ",
+    "ែ",
+    "ៃ",
+    "ោ",
+    "ៅ",
+    "ំ",
+    "ះ",
+    "ៈ",
+    "៉",
+    "៊",
+    "់",
+    "៌",
+    "៍",
+    "៎",
+    "៏",
+    "័",
+    "៑",
+    "្",
+    "៓",
+    "។",
+    "៕",
+    "៖",
+    "ៗ",
+    "៘",
+    "៙",
+    "៚",
+    "៛",
+    "ៜ",
+    "០",
+    "១",
+    "២",
+    "៣",
+    "៤",
+    "៥",
+    "៦",
+    "៧",
+    "៨",
+    "៩",
+    " "
+  ],
+  "dataset_names": [
+    "seanghay/khmer_grkpp_speech",
+    "seanghay/km-speech-corpus",
+    "KrorngAI/fleurs_openslr42_mpwt"
+  ],
+  "max_samples_per_dataset": 3000,
+  "data_cache_path": "Panhapich/kgs_ksc_fom",
+}