Upload WhisperForConditionalGeneration

README.md

@@ -14,8 +14,8 @@ model-index:
 - name: Whisper Medium Korean
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: Zeroth Korean
       type: kresnik/zeroth_korean
@@ -23,9 +23,9 @@ model-index:
       split: test
       args: 'split: test'
     metrics:
-    - name: Test Wer
-      type: wer
+    - type: wer
       value: 3.6440295136274656
+      name: Test Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

config.json

@@ -1,7 +1,8 @@
 {
-  "_name_or_path": "openai/whisper-medium",
+  "_name_or_path": "seastar105/whisper-medium-ko-zeroth",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "apply_spec_augment": false,
   "architectures": [
     "WhisperForConditionalGeneration"
   ],
@@ -11,6 +12,7 @@
     50257
   ],
   "bos_token_id": 50257,
+  "classifier_proj_size": 256,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
@@ -26,9 +28,16 @@
   "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
   "max_length": 448,
   "max_source_positions": 1500,
   "max_target_positions": 448,
+  "median_filter_width": 7,
   "model_type": "whisper",
   "num_hidden_layers": 24,
   "num_mel_bins": 80,
@@ -36,7 +45,8 @@
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0.dev0",
+  "transformers_version": "4.41.2",
   "use_cache": true,
+  "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "suppress_tokens": [],
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c172f1e20416047328218dfa55f65203afcbbdc79d6c6d5fa01124355d477b8
+size 3055544304