Model save

README.md

@@ -0,0 +1,95 @@
+---
+base_model: nadsoft/Hamsa-large-v0.1-beta
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: hamsa-pretrained
+  results: []
+---
+
+<!-- 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. -->
+
+# hamsa-pretrained
+
+This model is a fine-tuned version of [nadsoft/Hamsa-large-v0.1-beta](https://huggingface.co/nadsoft/Hamsa-large-v0.1-beta) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4344
+- Wer: 29.2057
+
+## 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: 0.00025
+- train_batch_size: 8
+- eval_batch_size: 4
+- 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: 35000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer     |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|
+| 1.895         | 0.01  | 1000  | 1.8765          | 86.7012 |
+| 1.6569        | 0.01  | 2000  | 1.5809          | 84.0907 |
+| 1.3312        | 0.02  | 3000  | 1.3458          | 75.7090 |
+| 1.2369        | 0.02  | 4000  | 1.2389          | 73.1365 |
+| 1.1518        | 0.03  | 5000  | 1.1097          | 66.8170 |
+| 1.0135        | 0.03  | 6000  | 1.0616          | 65.1843 |
+| 1.0965        | 0.04  | 7000  | 1.0084          | 65.8582 |
+| 0.867         | 0.04  | 8000  | 0.9305          | 57.6093 |
+| 0.9425        | 0.05  | 9000  | 0.8907          | 55.4854 |
+| 0.9501        | 0.05  | 10000 | 0.8393          | 54.0212 |
+| 0.8602        | 0.06  | 11000 | 0.8096          | 53.4968 |
+| 0.7596        | 0.06  | 12000 | 0.7761          | 51.9305 |
+| 0.7334        | 0.07  | 13000 | 0.7694          | 49.4411 |
+| 0.708         | 0.07  | 14000 | 0.7336          | 47.0040 |
+| 0.7112        | 0.08  | 15000 | 0.7149          | 47.5783 |
+| 0.6989        | 0.08  | 16000 | 0.6713          | 44.2986 |
+| 0.7025        | 0.09  | 17000 | 0.6639          | 43.7481 |
+| 0.6127        | 0.09  | 18000 | 0.6477          | 42.9127 |
+| 0.6342        | 0.1   | 19000 | 0.6298          | 42.6826 |
+| 0.6174        | 0.1   | 20000 | 0.6080          | 40.1172 |
+| 0.5551        | 0.11  | 21000 | 0.5896          | 39.0398 |
+| 0.5353        | 0.11  | 22000 | 0.5753          | 39.1253 |
+| 0.5528        | 0.12  | 23000 | 0.5588          | 40.2881 |
+| 0.5423        | 0.12  | 24000 | 0.5445          | 35.6606 |
+| 0.5069        | 0.13  | 25000 | 0.5304          | 35.9358 |
+| 0.4356        | 0.13  | 26000 | 0.5187          | 34.4930 |
+| 0.5111        | 0.14  | 27000 | 0.5035          | 33.4227 |
+| 0.5613        | 0.14  | 28000 | 0.4912          | 33.0952 |
+| 0.4165        | 0.15  | 29000 | 0.4825          | 32.0155 |
+| 0.4736        | 0.15  | 30000 | 0.4716          | 32.0914 |
+| 0.4213        | 0.16  | 31000 | 0.4618          | 31.6026 |
+| 0.4242        | 0.16  | 32000 | 0.4514          | 30.3757 |
+| 0.3837        | 0.17  | 33000 | 0.4448          | 30.3116 |
+| 0.4321        | 0.17  | 34000 | 0.4377          | 29.4691 |
+| 0.4268        | 0.18  | 35000 | 0.4344          | 29.2057 |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.2.dev0
+- Tokenizers 0.15.0

generation_config.json

@@ -0,0 +1,320 @@
+{
+  "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,
+      3
+    ],
+    [
+      22,
+      9
+    ],
+    [
+      22,
+      12
+    ],
+    [
+      23,
+      5
+    ],
+    [
+      23,
+      7
+    ],
+    [
+      23,
+      13
+    ],
+    [
+      25,
+      5
+    ],
+    [
+      26,
+      1
+    ],
+    [
+      26,
+      12
+    ],
+    [
+      27,
+      15
+    ]
+  ],
+  "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
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "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": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "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": "4.37.0.dev0"
+}