ImanNalia/FT_Wav2Vec2_Base_No_LM_30

README.md

@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # base
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None 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: 1.4338
-- Wer: 46.6971
-- Cer: 23.6416
+- Loss: 0.6689
+- Wer: 31.2258
+- Cer: 13.9975
 
 ## Model description
 
@@ -45,17 +45,17 @@ 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: 2000
-- num_epochs: 50
+- training_steps: 2700
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     | Cer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 4.2769        | 9.26  | 500  | 2.9188          | 99.9308 | 99.1103 |
-| 2.4426        | 18.52 | 1000 | 1.2869          | 64.5340 | 29.9360 |
-| 0.65          | 27.78 | 1500 | 1.2520          | 49.7577 | 24.1951 |
-| 0.3121        | 37.04 | 2000 | 1.3616          | 49.4391 | 24.7776 |
-| 0.187         | 46.3  | 2500 | 1.4338          | 46.6971 | 23.6416 |
+| 4.3822        | 1.4   | 500  | 2.9318          | 100.0   | 99.3341 |
+| 2.7693        | 2.81  | 1000 | 1.7387          | 90.0629 | 50.4533 |
+| 0.9915        | 4.21  | 1500 | 0.7714          | 41.5179 | 18.1139 |
+| 0.6189        | 5.62  | 2000 | 0.7052          | 35.2091 | 15.8310 |
+| 0.4696        | 7.02  | 2500 | 0.6689          | 31.2258 | 13.9975 |
 
 
 ### Framework versions

config.json

@@ -46,7 +46,7 @@
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
-  "dropout": 0.2,
+  "dropout": 0.1,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_norm": "group",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8338d66a3bc159a7e49299b4d11d3cec4e8ccf7a8c416ed95dc5b3b8222d9703
+oid sha256:3617d09fa080565cf6d45cc36d4c3c595a9bc0ceb75df180b445cdfb07c67454
 size 377611072

runs/Apr07_20-49-39_nmjehjx1et/events.out.tfevents.1712523679.nmjehjx1et.82.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0afdc3d6b0688efa3be340d58eb1a35deb9ab070e5ad0698b0862e81d97e6d57
+size 6338

runs/Apr07_21-05-46_nmjehjx1et/events.out.tfevents.1712524645.nmjehjx1et.82.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6214f9be75ec14e16081c1ad4daf5811ae43fc9c4c69013bc833500dfc5d027
+size 9575

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a13390488f07918d304364c62c0fc2a237a0263fddfc9443c017648041c69bc
+oid sha256:7bf1b3b3dc7791b2099d4b80a709f97337cb4b5149c3a539ba8118cb220cb2e5
 size 4527