End of training

README.md

@@ -0,0 +1,101 @@
+---
+language:
+- hi
+license: apache-2.0
+base_model: openai/whisper-medium
+tags:
+- generated_from_trainer
+datasets:
+- google/fleurs
+metrics:
+- wer
+model-index:
+- name: Whisper Medium Hindi -megha sharma
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Google Fleurs
+      type: google/fleurs
+      config: hi_in
+      split: None
+      args: 'config: hi, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 18.02030456852792
+---
+
+<!-- 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 Medium Hindi -megha sharma
+
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Google Fleurs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4333
+- Wer: 18.0203
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 25000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Wer     |
+|:-------------:|:-------:|:-----:|:---------------:|:-------:|
+| 0.0669        | 3.3898  | 1000  | 0.2086          | 20.9684 |
+| 0.0115        | 6.7797  | 2000  | 0.2637          | 19.7579 |
+| 0.0034        | 10.1695 | 3000  | 0.3012          | 19.6408 |
+| 0.0026        | 13.5593 | 4000  | 0.3179          | 19.2893 |
+| 0.0014        | 16.9492 | 5000  | 0.3242          | 18.7817 |
+| 0.0024        | 20.3390 | 6000  | 0.3348          | 19.1624 |
+| 0.0024        | 23.7288 | 7000  | 0.3421          | 19.7774 |
+| 0.0006        | 27.1186 | 8000  | 0.3511          | 18.6939 |
+| 0.0008        | 30.5085 | 9000  | 0.3632          | 18.8989 |
+| 0.0007        | 33.8983 | 10000 | 0.3600          | 18.7622 |
+| 0.0006        | 37.2881 | 11000 | 0.3470          | 18.4791 |
+| 0.0002        | 40.6780 | 12000 | 0.3548          | 18.2936 |
+| 0.0001        | 44.0678 | 13000 | 0.3711          | 18.0594 |
+| 0.0006        | 47.4576 | 14000 | 0.3733          | 18.2839 |
+| 0.0003        | 50.8475 | 15000 | 0.3766          | 18.1667 |
+| 0.0           | 54.2373 | 16000 | 0.3745          | 18.0203 |
+| 0.0           | 57.6271 | 17000 | 0.3914          | 17.8739 |
+| 0.0           | 61.0169 | 18000 | 0.4003          | 17.9032 |
+| 0.0           | 64.4068 | 19000 | 0.4081          | 17.8641 |
+| 0.0           | 67.7966 | 20000 | 0.4153          | 17.8544 |
+| 0.0           | 71.1864 | 21000 | 0.4219          | 17.8544 |
+| 0.0           | 74.5763 | 22000 | 0.4281          | 18.0105 |
+| 0.0           | 77.9661 | 23000 | 0.4333          | 18.0203 |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,240 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "language": "hindi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.44.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cbfeb96d6064ffce34b8aef42647bdcb5a64d3a82dca58cefb66afa56fc4d14
+oid sha256:d3748c09ca5d76936640809fc7dc17e4b91ad0335383eb65ca140c0da3c95c0d
 size 3055544304

runs/Aug29_07-13-25_speech-to-text-vm/events.out.tfevents.1724915617.speech-to-text-vm.3111198.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c147692f5bcb2ede9693032db31482e0647980d9c8790e5a614d8922f17fbd
-size 111676
+oid sha256:260e46c56d3cad62df43d1aaebb7f237c3a4833d50cf8e51a6df2e06a247a9e6
+size 112036