End of training

README.md

@@ -1,40 +1,23 @@
 ---
 language:
 - ml
-license: mit
+license: apache-2.0
+base_model: openai/whisper-small
 tags:
-- whisper-event
-- hf-asr-leaderboard
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_11_0
-metrics:
-- wer
-base_model: openai/whisper-small
+- mozilla-foundation/common_voice_13_0
 model-index:
-- name: whisper_malayalam_largev2
-  results:
-  - task:
-      type: automatic-speech-recognition
-      name: Automatic Speech Recognition
-    dataset:
-      name: mozilla-foundation/common_voice_11_0
-      type: mozilla-foundation/common_voice_11_0
-      config: ml
-      split: test
-    metrics:
-    - type: wer
-      value: 84.36781609195401
-      name: Wer
+- name: Whisper Small Malayalam - Kavya Manohar
+  results: []
 ---
 
-# Whisper-fineTuning-malayalam
+<!-- 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. -->
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
-It achieves the following results on the evaluation set:
+# Whisper Small Malayalam - Kavya Manohar
 
-    Loss: 0.5664
-    Wer: 84.3678
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
 
 ## Model description
 
@@ -54,27 +37,17 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 12
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 1000
-- mixed_precision_training: Native AMP
-
-### Training results
-
- 	27.78 	1000 	 	
-
-| Training Loss | Epoch | Step | Validation Loss | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0003        | 27.78 | 1000 | 0.5664          | 84.3678 |
-
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 50
+- training_steps: 500
 
 ### Framework versions
 
-- Transformers 4.26.0.dev0
-- Pytorch 1.13.0+cu116
-- Datasets 2.8.0
-- Tokenizers 0.13.2
+- Transformers 4.33.3
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

generation_config.json

@@ -1,96 +1,44 @@
 {
   "alignment_heads": [
     [
-      10,
-      12
-    ],
-    [
-      13,
-      17
-    ],
-    [
-      16,
-      11
-    ],
-    [
-      16,
-      12
-    ],
-    [
-      16,
-      13
-    ],
-    [
-      17,
-      15
-    ],
-    [
-      17,
-      16
-    ],
-    [
-      18,
-      4
-    ],
-    [
-      18,
-      11
-    ],
-    [
-      18,
-      19
-    ],
-    [
-      19,
-      11
-    ],
-    [
-      21,
-      2
-    ],
-    [
-      21,
-      3
-    ],
-    [
-      22,
+      5,
       3
     ],
     [
-      22,
+      5,
       9
     ],
     [
-      22,
-      12
+      8,
+      0
     ],
     [
-      23,
-      5
+      8,
+      4
     ],
     [
-      23,
+      8,
       7
     ],
     [
-      23,
-      13
+      8,
+      8
     ],
     [
-      25,
-      5
+      9,
+      0
     ],
     [
-      26,
-      1
+      9,
+      7
     ],
     [
-      26,
-      12
+      9,
+      9
     ],
     [
-      27,
-      15
+      10,
+      5
     ]
   ],
   "begin_suppress_tokens": [

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c9574ff2b03a12db1679e0bed9c65ff6068b34d6f77e369cd76cabf043a515
-size 967102729
+oid sha256:55b01a43f8ad46754c18f9ec9fe2e066ef91975863b135699b07edbb0c0cff28
+size 967096009

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a90ce4dea18bb0faa363deb0cd2146948a0f17c5b9a0e284d1d317069e312f
+oid sha256:1e76e435e8d0911d081c337a92be220eb31366515caedec24857a54154ab14c7
 size 4219