End of training

README.md

@@ -7,24 +7,9 @@ tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_13_0
-metrics:
-- wer
 model-index:
 - name: Whisper Small MN - Ochirsukh Batbold
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 13
-      type: mozilla-foundation/common_voice_13_0
-      config: dv
-      split: test
-      args: dv
-    metrics:
-    - name: Wer
-      type: wer
-      value: 10.948638592342734
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,11 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Small MN - Ochirsukh Batbold
 
-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: 0.3325
-- Wer Ortho: 57.9010
-- Wer: 10.9486
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 mn dataset.
 
 ## Model description
 
@@ -62,21 +43,11 @@ 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: 4000
+- training_steps: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.0653        | 3.25  | 500  | 0.1639          | 59.6699   | 12.2944 |
-| 0.017         | 6.49  | 1000 | 0.2145          | 59.4888   | 12.0458 |
-| 0.0069        | 9.74  | 1500 | 0.2668          | 58.0611   | 11.4042 |
-| 0.0046        | 12.99 | 2000 | 0.2806          | 58.4233   | 11.5155 |
-| 0.0033        | 16.23 | 2500 | 0.3095          | 58.0333   | 11.3277 |
-| 0.0027        | 19.48 | 3000 | 0.3080          | 56.8424   | 11.3207 |
-| 0.0018        | 22.73 | 3500 | 0.3264          | 57.0235   | 11.2042 |
-| 0.0025        | 25.97 | 4000 | 0.3325          | 57.9010   | 10.9486 |
 
 
 ### Framework versions

generation_config.json

@@ -51,15 +51,11 @@
   "forced_decoder_ids": [
     [
       1,
-      50314
+      null
     ],
     [
       2,
       50359
-    ],
-    [
-      3,
-      50363
     ]
   ],
   "is_multilingual": true,
@@ -164,7 +160,6 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "mongolian",
   "max_initial_timestamp_index": 1,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -260,7 +255,6 @@
     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 sha256:5074116cd67ec8629205253f06636a23669d3e4596f23103b354b66186bb648e
+oid sha256:a33a0b0a7af78f505e023259d2fc12d29d7b8515dcf3db2cad9d656b73ef6047
 size 966995080

runs/Nov23_09-22-46_icdcub-03/events.out.tfevents.1700731368.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b41fc1d7316e8bd77e07c535beb6b1a2bac69ad27a6b08fd2aed56704fc1d17
+size 5946

runs/Nov23_09-25-42_icdcub-03/events.out.tfevents.1700731544.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be806eacc6b798cc267195578cd7faaaeccbc8dbd510c158b2929cce82e86d73
+size 6291

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db49629d3fa589b0124e9ed0aa0ff2b003656791f195bff7b6b3e21516fdaa3c
+oid sha256:07d958002d413e194073c59c4a5b6801ab9a4e25d7dc51427fc04e7ed44a3146
 size 4283