End of training
Browse files
README.md
CHANGED
|
@@ -1,19 +1,37 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: openai/whisper-medium
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
-
- name:
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
#
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -39,7 +57,7 @@ The following hyperparameters were used during training:
|
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- lr_scheduler_warmup_steps: 0.03
|
| 42 |
-
- training_steps:
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- ga
|
| 4 |
+
- en
|
| 5 |
license: apache-2.0
|
| 6 |
base_model: openai/whisper-medium
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- ymoslem/IWSLT2023-GA-EN
|
| 11 |
+
- ymoslem/FLEURS-GA-EN
|
| 12 |
+
- ymoslem/BitesizeIrish-GA-EN
|
| 13 |
+
- ymoslem/SpokenWords-GA-EN-MTed
|
| 14 |
model-index:
|
| 15 |
+
- name: Whisper Medium GA-EN Speech Translation
|
| 16 |
results: []
|
| 17 |
---
|
| 18 |
|
| 19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 20 |
should probably proofread and complete it, then remove this comment. -->
|
| 21 |
|
| 22 |
+
# Whisper Medium GA-EN Speech Translation
|
| 23 |
|
| 24 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the IWSLT-2023, FLEURS, BiteSize, SpokenWords, Tatoeba, and Wikimedia dataset.
|
| 25 |
+
It achieves the following results on the evaluation set:
|
| 26 |
+
- epoch: 0.49
|
| 27 |
+
- eval_bleu: 30.37
|
| 28 |
+
- eval_chrf: 50.78
|
| 29 |
+
- eval_loss: 1.0718
|
| 30 |
+
- eval_runtime: 116.0928
|
| 31 |
+
- eval_samples_per_second: 2.989
|
| 32 |
+
- eval_steps_per_second: 0.19
|
| 33 |
+
- eval_wer: 68.6628
|
| 34 |
+
- step: 1500
|
| 35 |
|
| 36 |
## Model description
|
| 37 |
|
|
|
|
| 57 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 58 |
- lr_scheduler_type: linear
|
| 59 |
- lr_scheduler_warmup_steps: 0.03
|
| 60 |
+
- training_steps: 2000
|
| 61 |
- mixed_precision_training: Native AMP
|
| 62 |
|
| 63 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055544304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06a92d9a317a64686dc2a3fe8ee48db618737252a72793a5a4ecb939a64152d7
|
| 3 |
size 3055544304
|
runs/Apr16_07-34-37_3b47d5351b33/events.out.tfevents.1713252897.3b47d5351b33
ADDED
|
Binary file (5.43 kB). View file
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4667
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08788ba50c4ba935f9ddd9a7c67b9ed2f5611398e83aaf44cd34cc5f1f85b91f
|
| 3 |
size 4667
|