End of training
Browse files
README.md
CHANGED
|
@@ -8,9 +8,24 @@ tags:
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_13_0
|
|
|
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: Whisper Small Tr - Evren Ozkip
|
| 13 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -19,6 +34,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# Whisper Small Tr - Evren Ozkip
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -44,7 +63,7 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: constant_with_warmup
|
| 46 |
- lr_scheduler_warmup_steps: 50
|
| 47 |
-
- training_steps:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
|
|
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- mozilla-foundation/common_voice_13_0
|
| 11 |
+
metrics:
|
| 12 |
+
- wer
|
| 13 |
model-index:
|
| 14 |
- name: Whisper Small Tr - Evren Ozkip
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Automatic Speech Recognition
|
| 18 |
+
type: automatic-speech-recognition
|
| 19 |
+
dataset:
|
| 20 |
+
name: Common Voice 13
|
| 21 |
+
type: mozilla-foundation/common_voice_13_0
|
| 22 |
+
config: tr
|
| 23 |
+
split: test
|
| 24 |
+
args: tr
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Wer
|
| 27 |
+
type: wer
|
| 28 |
+
value: 55.714285714285715
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
# Whisper Small Tr - Evren Ozkip
|
| 35 |
|
| 36 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 4.1107
|
| 39 |
+
- Wer Ortho: 55.7143
|
| 40 |
+
- Wer: 55.7143
|
| 41 |
|
| 42 |
## Model description
|
| 43 |
|
|
|
|
| 63 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 64 |
- lr_scheduler_type: constant_with_warmup
|
| 65 |
- lr_scheduler_warmup_steps: 50
|
| 66 |
+
- training_steps: 10
|
| 67 |
- mixed_precision_training: Native AMP
|
| 68 |
|
| 69 |
### Training results
|
config.json
CHANGED
|
@@ -52,7 +52,7 @@
|
|
| 52 |
"num_mel_bins": 80,
|
| 53 |
"pad_token_id": 50257,
|
| 54 |
"scale_embedding": false,
|
| 55 |
-
"torch_dtype": "
|
| 56 |
"transformers_version": "4.51.3",
|
| 57 |
"use_cache": false,
|
| 58 |
"use_weighted_layer_sum": false,
|
|
|
|
| 52 |
"num_mel_bins": 80,
|
| 53 |
"pad_token_id": 50257,
|
| 54 |
"scale_embedding": false,
|
| 55 |
+
"torch_dtype": "float16",
|
| 56 |
"transformers_version": "4.51.3",
|
| 57 |
"use_cache": false,
|
| 58 |
"use_weighted_layer_sum": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e98c584850392cb0b5276d31bca4bfd21b933090339e4d960c3371346cf5651
|
| 3 |
+
size 483525200
|
runs/May13_08-11-00_n37ffspdu9/events.out.tfevents.1747124024.n37ffspdu9.1017.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:778d669085a1cce4957926633a43724716d47e1879bce632a2c4d7b80b8ee405
|
| 3 |
+
size 452
|