End of training

README.md

@@ -16,13 +16,13 @@ model-index:
     dataset:
       name: common_voice_13_0
       type: common_voice_13_0
-      config: ta
+      config: hi
       split: test
-      args: ta
+      args: hi
     metrics:
     - name: Wer
       type: wer
-      value: 0.5893832943013271
+      value: 0.5216572504708098
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7021
-- Wer: 0.5894
+- Loss: 0.9408
+- Wer: 0.5217
 
 ## Model description
 
@@ -68,9 +68,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.5892        | 6.4   | 800  | 0.6134          | 0.6987 |
-| 0.134         | 12.8  | 1600 | 0.6760          | 0.6354 |
-| 0.0698        | 19.2  | 2400 | 0.7021          | 0.5894 |
+| 1.1749        | 6.4   | 800  | 0.9206          | 0.6466 |
+| 0.2218        | 12.8  | 1600 | 0.9543          | 0.5581 |
+| 0.1143        | 19.2  | 2400 | 0.9408          | 0.5217 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271f3465dd342d185bd916a7aa5502de420c609cf73b5c250e142a767eccc4e0
+oid sha256:8ae15396fbacd8f6c9fddd976cc303c961914c75b3afffd279151e6cd64eeac7
 size 1262213380

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

runs/Apr13_14-57-42_cb2c75f052a1/events.out.tfevents.1713020348.cb2c75f052a1.3520.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8101c33533f14ff59e83512cae9b6d85d5c6e3988b8128fdf15471a2a2bf337
-size 8275
+oid sha256:39e96997614d3e1dadc0fb33a01991e8fae3a698ee4e84914106c8e8a2fea3c8
+size 8629