Training in progress, step 100

README.md

@@ -1,24 +1,24 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-base
+base_model: zainulhakim/240615-wav2vec2-ASR-Arabs
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: 240615-wav2vec2-ASR-Chinese
+- name: 240624-wav2vec2-ASR-Arab
   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. -->
 
-# 240615-wav2vec2-ASR-Chinese
+# 240624-wav2vec2-ASR-Arab
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
+This model is a fine-tuned version of [zainulhakim/240615-wav2vec2-ASR-Arabs](https://huggingface.co/zainulhakim/240615-wav2vec2-ASR-Arabs) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2831
-- Wer: 0.2399
+- Loss: 1.4394
+- Wer: 0.9293
 
 ## Model description
 
@@ -44,17 +44,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 30
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 6.25  | 100  | 1.2831          | 0.2399 |
-| No log        | 12.5  | 200  | 1.2996          | 0.2657 |
-| No log        | 18.75 | 300  | 1.3705          | 0.3092 |
-| No log        | 25.0  | 400  | 1.3119          | 0.3269 |
+| No log        | 6.25  | 100  | 2.5463          | 1.0    |
+| No log        | 12.5  | 200  | 1.4375          | 1.0    |
+| No log        | 18.75 | 300  | 1.4394          | 0.9293 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "zainulhakim/240624-wav2vec2-ASR-Indian",
+  "_name_or_path": "zainulhakim/240624-wav2vec2-ASR-Arab",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d58c9d6b45b19643af2453676f183cbf0ebb5e97439f71407e979970fe44258
+size 377611120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce20e709fcd71cb443f2e388fec2ecb77de152731ce933ae6ff74a5e4e39b274
-size 5112
+oid sha256:c9cc2bacb48d98e40137f8ec269a8280c999b83ed820a1287b62314043915c03
+size 5176