Upload WhisperForConditionalGeneration

README.md

@@ -1,20 +1,20 @@
 ---
-library_name: transformers
-language:
-- vi
 base_model: openai/whisper-small-v3
-tags:
-- generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_11_0
+language:
+- vi
+library_name: transformers
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: Whisper small vi - Ox
   results:
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: Common Voice 11.0
       type: mozilla-foundation/common_voice_11_0
@@ -22,9 +22,9 @@ model-index:
       split: test
       args: 'config: vi, split: test'
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 14.738458164272398
+      name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "linl03/whisper-large-v3-vi",
+  "_name_or_path": "linl03/whisper-small-vi",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

generation_config.json

@@ -1,44 +1,36 @@
 {
   "alignment_heads": [
     [
-      5,
-      3
-    ],
-    [
-      5,
-      9
+      3,
+      1
     ],
     [
-      8,
-      0
+      4,
+      2
     ],
     [
-      8,
-      4
+      4,
+      3
     ],
     [
-      8,
+      4,
       7
     ],
     [
-      8,
-      8
-    ],
-    [
-      9,
-      0
+      5,
+      1
     ],
     [
-      9,
-      7
+      5,
+      2
     ],
     [
-      9,
-      9
+      5,
+      4
     ],
     [
-      10,
-      5
+      5,
+      6
     ]
   ],
   "begin_suppress_tokens": [
@@ -48,6 +40,16 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
@@ -150,7 +152,6 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "vi",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -241,11 +242,12 @@
     49870,
     50254,
     50258,
+    50358,
+    50359,
     50360,
     50361,
     50362
   ],
-  "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68c9b74b9b76cd3a9ad980a314381d862d36ef5d654f1c37b97c5464ac1c7df
+oid sha256:9e3c9a1451c4a1abb56ff3e11b3e6b7b8f444e189e161f21950a1a104cd724a1
 size 966995080