Upload WhisperForConditionalGeneration

README.md

@@ -1,20 +1,20 @@
 ---
-language:
-- vi
-license: apache-2.0
 base_model: openai/whisper-small
-tags:
-- generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_11_0
+language:
+- vi
+license: apache-2.0
 metrics:
 - wer
+tags:
+- generated_from_trainer
 model-index:
 - name: Whisper Small Vi - Sonkn
   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: None
       args: 'config: vi, split: test'
     metrics:
-    - name: Wer
-      type: wer
+    - type: wer
       value: 28.775084987388965
+      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": "openai/whisper-small",
+  "_name_or_path": "sonkn/whisper-small-vi",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

generation_config.json

@@ -48,6 +48,16 @@
   "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 +160,6 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "vi",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -247,7 +256,6 @@
     50361,
     50362
   ],
-  "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358