End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2088
-- Cer: 0.0756
-- Wer: 0.4205
+- Loss: 0.1886
+- Cer: 0.0713
+- Wer: 0.3995
 
 ## Model description
 
@@ -48,17 +48,22 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Cer    | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
-| 0.4056        | 1.1114 | 200  | 0.2414          | 0.0824 | 0.4542 |
-| 0.337         | 2.2228 | 400  | 0.2207          | 0.0778 | 0.4315 |
-| 0.3029        | 3.3343 | 600  | 0.2127          | 0.0770 | 0.4301 |
-| 0.288         | 4.4457 | 800  | 0.2088          | 0.0756 | 0.4205 |
+| 0.3941        | 1.1114 | 200  | 0.2399          | 0.0845 | 0.4563 |
+| 0.3327        | 2.2228 | 400  | 0.2173          | 0.0776 | 0.4271 |
+| 0.3033        | 3.3343 | 600  | 0.2103          | 0.0771 | 0.4290 |
+| 0.288         | 4.4457 | 800  | 0.2085          | 0.0751 | 0.4172 |
+| 0.2646        | 5.5571 | 1000 | 0.1984          | 0.0740 | 0.4130 |
+| 0.2616        | 6.6685 | 1200 | 0.1974          | 0.0726 | 0.4052 |
+| 0.2385        | 7.7799 | 1400 | 0.1950          | 0.0737 | 0.4014 |
+| 0.2265        | 8.8914 | 1600 | 0.1892          | 0.0715 | 0.4003 |
+| 0.2392        | 10.0   | 1800 | 0.1886          | 0.0713 | 0.3995 |
 
 
 ### Framework versions

adapter.ttj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42cca513961a5986fffd331708485745ed4d711c56edc1bb3cad85f0e74fb173
+size 8947144

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070748102102ff7f0aaadaf2e85efd8c867a950b95a3ca53e618ff7bf7d74e8a
+oid sha256:40a3b62468d8c8efed637227acda4c69cadec38793f6f3603eb79369e1578fa8
 size 3859039520

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04defc10cea1e72f6299dd544b9114920da9841c9bf809b41c8ddb90301e30e9
+oid sha256:3d7baca88f25ee9c776cb19b06e696ad314935ff300cdc3ec54ea3e6fc9246b5
 size 6097

vocab.json

@@ -1,62 +1 @@
-{
-  "ttj": {
-    "&": 40,
-    "'": 3,
-    "-": 31,
-    "1": 37,
-    "A": 19,
-    "B": 30,
-    "C": 26,
-    "D": 6,
-    "E": 24,
-    "F": 27,
-    "G": 13,
-    "H": 5,
-    "I": 41,
-    "K": 38,
-    "L": 52,
-    "M": 34,
-    "N": 49,
-    "O": 33,
-    "P": 42,
-    "Q": 21,
-    "R": 10,
-    "S": 51,
-    "T": 35,
-    "U": 44,
-    "W": 55,
-    "Y": 53,
-    "[PAD]": 57,
-    "[UNK]": 56,
-    "a": 17,
-    "b": 16,
-    "bb": 50,
-    "c": 2,
-    "d": 22,
-    "e": 9,
-    "f": 48,
-    "g": 14,
-    "h": 28,
-    "i": 36,
-    "j": 45,
-    "k": 43,
-    "l": 0,
-    "m": 46,
-    "n": 15,
-    "ny": 11,
-    "o": 39,
-    "p": 1,
-    "r": 25,
-    "s": 4,
-    "t": 18,
-    "u": 29,
-    "v": 7,
-    "w": 32,
-    "y": 47,
-    "z": 54,
-    "|": 12,
-    "ö": 8,
-    "ü": 20,
-    "ę": 23
-  }
-}
+{"ttj": {"l": 0, "p": 1, "c": 2, "'": 3, "s": 4, "H": 5, "D": 6, "v": 7, "\u00f6": 8, "e": 9, "R": 10, "ny": 11, "G": 13, "g": 14, "n": 15, "b": 16, "a": 17, "t": 18, "A": 19, "\u00fc": 20, "Q": 21, "d": 22, "\u0119": 23, "E": 24, "r": 25, "C": 26, "F": 27, "h": 28, "u": 29, "B": 30, "-": 31, "w": 32, "O": 33, "M": 34, "T": 35, "i": 36, "1": 37, "K": 38, "o": 39, "&": 40, "I": 41, "P": 42, "k": 43, "U": 44, "j": 45, "m": 46, "y": 47, "f": 48, "N": 49, "bb": 50, "S": 51, "L": 52, "Y": 53, "z": 54, "W": 55, "|": 12, "[UNK]": 56, "[PAD]": 57}}