End of training

README.md

@@ -2,7 +2,7 @@
 language:
 - yo
 license: apache-2.0
-base_model: EYEDOL/Yoruba-ASR
+base_model: neoform-ai/whisper-medium-yoruba
 tags:
 - whisper-event
 - generated_from_trainer
@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 58.53720050441362
+      value: 47.204707860445566
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,10 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # YorubaASR2
 
-This model is a fine-tuned version of [EYEDOL/Yoruba-ASR](https://huggingface.co/EYEDOL/Yoruba-ASR) on the Common Voice 17.0 dataset.
+This model is a fine-tuned version of [neoform-ai/whisper-medium-yoruba](https://huggingface.co/neoform-ai/whisper-medium-yoruba) on the Common Voice 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8161
-- Wer: 58.5372
+- Loss: 0.8390
+- Wer: 47.2047
 
 ## Model description
 
@@ -69,7 +69,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0158        | 3.8462 | 1000 | 0.8161          | 58.5372 |
+| 0.0145        | 3.8462 | 1000 | 0.8390          | 47.2047 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EYEDOL/Yoruba-ASR",
+  "_name_or_path": "neoform-ai/whisper-medium-yoruba",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -25,7 +25,20 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 24,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -43,7 +56,96 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "suppress_tokens": [],
+  "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
+  ],
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_cache": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3b9c9abc2d8b439cb59078068d74b664a724c570395cbf25abcac20cb960d2
+oid sha256:16ffa429fea34e24a04ea2c2a2c53a1616c1f0539502b821cc9823bc7a1f6351
 size 3055544304

runs/Jan14_15-52-48_bde1c362ad0c/events.out.tfevents.1736869969.bde1c362ad0c.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea8c9f4481f379f73c7b9277709eb98c86416a29952537f46dc758faaa17933
+size 15712

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0407d230531ea73609058990c97f41a1ea74cfe6c60ff391dfb72cdfba97c25a
+oid sha256:05134c492ee85caf4e98e6aaa61799ac091e39728eb935e61b233fd84d6e8ea7
 size 5240