End of training

README.md

@@ -1,23 +1,42 @@
 ---
 language:
-- dv
+- sr
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_13_0
+metrics:
+- wer
 model-index:
-- name: Whisper Small Dv - Sanchit Gandhi
-  results: []
+- name: Whisper Small Sr - Sagicc
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 13
+      type: mozilla-foundation/common_voice_13_0
+      config: sr
+      split: test
+      args: sr
+    metrics:
+    - name: Wer
+      type: wer
+      value: 18.092962641181582
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper Small Dv - Sanchit Gandhi
+# Whisper Small Sr - Sagicc
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3675
+- Wer Ortho: 28.9565
+- Wer: 18.0930
 
 ## Model description
 
@@ -43,7 +62,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
+| 0.0728        | 2.87  | 500  | 0.2978          | 29.5435   | 18.8749 |
+| 0.0318        | 5.75  | 1000 | 0.3675          | 28.9565   | 18.0930 |
+
 
 ### Framework versions
 

generation_config.json

@@ -51,11 +51,15 @@
   "forced_decoder_ids": [
     [
       1,
-      null
+      50303
     ],
     [
       2,
       50359
+    ],
+    [
+      3,
+      50363
     ]
   ],
   "is_multilingual": true,
@@ -160,6 +164,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "serbian",
   "max_initial_timestamp_index": 1,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -255,6 +260,7 @@
     50361,
     50362
   ],
+  "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358