End of training

README.md

@@ -0,0 +1,107 @@
+---
+library_name: transformers
+language:
+- lv
+license: apache-2.0
+base_model: openai/whisper-medium
+tags:
+- hf-asr-leaderboard
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_17_0
+metrics:
+- wer
+model-index:
+- name: Whisper medium LV - Felikss Kleins
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 17.0
+      type: mozilla-foundation/common_voice_17_0
+      config: lv
+      split: None
+      args: 'config: lv, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 11.938731026829945
+---
+
+<!-- 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 LV - Felikss Kleins
+
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2416
+- Wer: 11.9387
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 10000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| No log        | 0.02    | 200  | 0.2930          | 22.3576 |
+| 0.9797        | 1.0116  | 400  | 0.2359          | 18.2083 |
+| 0.357         | 2.0033  | 600  | 0.2274          | 16.4665 |
+| 0.2582        | 2.0233  | 800  | 0.2111          | 15.6402 |
+| 0.1718        | 3.0149  | 1000 | 0.2135          | 14.9883 |
+| 0.1718        | 4.0066  | 1200 | 0.2090          | 14.2294 |
+| 0.1355        | 4.0266  | 1400 | 0.2193          | 13.5537 |
+| 0.1024        | 5.0183  | 1600 | 0.2255          | 14.5048 |
+| 0.0836        | 6.0099  | 1800 | 0.2145          | 12.9751 |
+| 0.0699        | 7.0015  | 2000 | 0.2232          | 13.2129 |
+| 0.0699        | 7.0216  | 2200 | 0.2181          | 12.7155 |
+| 0.0598        | 8.0132  | 2400 | 0.2192          | 12.7076 |
+| 0.054         | 9.0048  | 2600 | 0.2348          | 13.0048 |
+| 0.0452        | 9.0249  | 2800 | 0.2241          | 13.0940 |
+| 0.0433        | 10.0165 | 3000 | 0.2406          | 12.6362 |
+| 0.0433        | 11.0082 | 3200 | 0.2283          | 12.5332 |
+| 0.0377        | 11.0282 | 3400 | 0.2293          | 12.2201 |
+| 0.0317        | 12.0198 | 3600 | 0.2323          | 12.6144 |
+| 0.0297        | 13.0114 | 3800 | 0.2309          | 12.2974 |
+| 0.0267        | 14.0031 | 4000 | 0.2342          | 11.9011 |
+| 0.0267        | 14.0231 | 4200 | 0.2286          | 12.1171 |
+| 0.0243        | 15.0147 | 4400 | 0.2364          | 12.0854 |
+| 0.0218        | 16.0064 | 4600 | 0.2405          | 12.1805 |
+| 0.021         | 16.0264 | 4800 | 0.2422          | 12.0338 |
+| 0.0173        | 17.0180 | 5000 | 0.2416          | 11.9387 |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.0.1
+- Datasets 3.0.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,249 @@
+{
+  "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,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "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
+  },
+  "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_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065547d2acfdeabfaf1b199e6a5807e588bcf5c3e0e584d957c76fad15803338
+oid sha256:353ca0d546316f47126405cca5cc5f3b255c4a66831e2ec003c06842b2f424f4
 size 3055544304