Training in progress, step 100

README.md

@@ -1,24 +1,24 @@
 ---
 license: apache-2.0
-base_model: zainulhakim/240615-wav2vec2-ASR-English
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: 240624-wav2vec2-ASR-English
+- name: 240615-wav2vec2-ASR-Chinese
   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. -->
 
-# 240624-wav2vec2-ASR-English
+# 240615-wav2vec2-ASR-Chinese
 
-This model is a fine-tuned version of [zainulhakim/240615-wav2vec2-ASR-English](https://huggingface.co/zainulhakim/240615-wav2vec2-ASR-English) on an unknown dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9959
-- Wer: 0.6623
+- Loss: 1.2831
+- Wer: 0.2399
 
 ## Model description
 
@@ -38,23 +38,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 4
+- train_batch_size: 5
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 20
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 5.0   | 100  | 2.6284          | 1.0    |
-| No log        | 10.0  | 200  | 0.8606          | 0.8831 |
-| No log        | 15.0  | 300  | 0.9080          | 0.7273 |
-| No log        | 20.0  | 400  | 0.9959          | 0.6623 |
+| 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 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "zainulhakim/240615-wav2vec2-ASR-English",
+  "_name_or_path": "zainulhakim/240624-wav2vec2-ASR-English",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
@@ -111,7 +111,7 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.42.4",
   "use_weighted_layer_sum": false,
   "vocab_size": 32,
   "xvector_output_dim": 512

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9db478e6997d1f77eb5ee4c1ac3d8678561999d3eea5f825ff9bf525bf2bef6
+oid sha256:0bea2699cab9176f6e327eb8c786ef813d615aaf1ce9b5e5206e68d10fd12e98
 size 377611120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1336d39022631cbcea7b1f77d0449764eb36a1dc2db9440784d4b5b13988ef7
+oid sha256:9bf86076300a0f2fab268bb82697736e6ad0aae4c81e54148fa41eb52e5ebbf9
 size 5112