End of training
Browse files- README.md +22 -2
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -3,12 +3,29 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/wav2vec2-large-lv60
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- librispeech_asr
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: wav2vec2-librispeech-clean-100h-demo-dist
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,7 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# wav2vec2-librispeech-clean-100h-demo-dist
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) on the
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/wav2vec2-large-lv60
|
| 5 |
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- librispeech_asr
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- librispeech_asr
|
| 11 |
+
metrics:
|
| 12 |
+
- wer
|
| 13 |
model-index:
|
| 14 |
- name: wav2vec2-librispeech-clean-100h-demo-dist
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Automatic Speech Recognition
|
| 18 |
+
type: automatic-speech-recognition
|
| 19 |
+
dataset:
|
| 20 |
+
name: LIBRISPEECH_ASR - CLEAN
|
| 21 |
+
type: librispeech_asr
|
| 22 |
+
config: clean
|
| 23 |
+
split: None
|
| 24 |
+
args: 'Config: clean, Training split: train.100, Eval split: validation'
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Wer
|
| 27 |
+
type: wer
|
| 28 |
+
value: 0.09198730662435542
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
|
| 34 |
# wav2vec2-librispeech-clean-100h-demo-dist
|
| 35 |
|
| 36 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) on the LIBRISPEECH_ASR - CLEAN dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.0554
|
| 39 |
+
- Wer: 0.0920
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.05542026832699776,
|
| 4 |
+
"eval_runtime": 105.5563,
|
| 5 |
+
"eval_samples": 2642,
|
| 6 |
+
"eval_samples_per_second": 25.029,
|
| 7 |
+
"eval_steps_per_second": 3.136,
|
| 8 |
+
"eval_wer": 0.09198730662435542,
|
| 9 |
+
"total_flos": 3.3190826326923264e+19,
|
| 10 |
+
"train_loss": 0.19606071691714266,
|
| 11 |
+
"train_runtime": 14592.9757,
|
| 12 |
+
"train_samples": 28538,
|
| 13 |
+
"train_samples_per_second": 5.867,
|
| 14 |
+
"train_steps_per_second": 1.467
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.05542026832699776,
|
| 4 |
+
"eval_runtime": 105.5563,
|
| 5 |
+
"eval_samples": 2642,
|
| 6 |
+
"eval_samples_per_second": 25.029,
|
| 7 |
+
"eval_steps_per_second": 3.136,
|
| 8 |
+
"eval_wer": 0.09198730662435542
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 3.3190826326923264e+19,
|
| 4 |
+
"train_loss": 0.19606071691714266,
|
| 5 |
+
"train_runtime": 14592.9757,
|
| 6 |
+
"train_samples": 28538,
|
| 7 |
+
"train_samples_per_second": 5.867,
|
| 8 |
+
"train_steps_per_second": 1.467
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|