End of training
Browse files- README.md +25 -2
- adapter.eng.safetensors +3 -0
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +51 -0
README.md
CHANGED
@@ -1,13 +1,33 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
tags:
|
|
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_15_0
|
|
|
|
|
8 |
model-index:
|
9 |
- name: RohitDataScienceSpeechAnalyticsOutput
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +35,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# RohitDataScienceSpeechAnalyticsOutput
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- hi
|
4 |
license: apache-2.0
|
5 |
base_model: facebook/wav2vec2-large-xlsr-53
|
6 |
tags:
|
7 |
+
- automatic-speech-recognition
|
8 |
+
- mozilla-foundation/common_voice_15_0
|
9 |
+
- mms
|
10 |
- generated_from_trainer
|
11 |
datasets:
|
12 |
- common_voice_15_0
|
13 |
+
metrics:
|
14 |
+
- wer
|
15 |
model-index:
|
16 |
- name: RohitDataScienceSpeechAnalyticsOutput
|
17 |
+
results:
|
18 |
+
- task:
|
19 |
+
name: Automatic Speech Recognition
|
20 |
+
type: automatic-speech-recognition
|
21 |
+
dataset:
|
22 |
+
name: MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI
|
23 |
+
type: common_voice_15_0
|
24 |
+
config: hi
|
25 |
+
split: validation
|
26 |
+
args: 'Config: hi, Training split: train, Eval split: validation'
|
27 |
+
metrics:
|
28 |
+
- name: Wer
|
29 |
+
type: wer
|
30 |
+
value: 1.0016248153618907
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# RohitDataScienceSpeechAnalyticsOutput
|
37 |
|
38 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI dataset.
|
39 |
+
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 20.2731
|
41 |
+
- Wer: 1.0016
|
42 |
|
43 |
## Model description
|
44 |
|
adapter.eng.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec5de473cb31f6139fe6b8628ed6f885991fa449f9c978694a0f3816c28e15d6
|
3 |
+
size 3918936
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 20.27312660217285,
|
4 |
+
"eval_runtime": 82.4708,
|
5 |
+
"eval_samples": 2416,
|
6 |
+
"eval_samples_per_second": 29.295,
|
7 |
+
"eval_steps_per_second": 3.662,
|
8 |
+
"eval_wer": 1.0016248153618907,
|
9 |
+
"total_flos": 6.105598680744346e+17,
|
10 |
+
"train_loss": 18.517574757543102,
|
11 |
+
"train_runtime": 376.588,
|
12 |
+
"train_samples": 4630,
|
13 |
+
"train_samples_per_second": 12.295,
|
14 |
+
"train_steps_per_second": 0.385
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 20.27312660217285,
|
4 |
+
"eval_runtime": 82.4708,
|
5 |
+
"eval_samples": 2416,
|
6 |
+
"eval_samples_per_second": 29.295,
|
7 |
+
"eval_steps_per_second": 3.662,
|
8 |
+
"eval_wer": 1.0016248153618907
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 6.105598680744346e+17,
|
4 |
+
"train_loss": 18.517574757543102,
|
5 |
+
"train_runtime": 376.588,
|
6 |
+
"train_samples": 4630,
|
7 |
+
"train_samples_per_second": 12.295,
|
8 |
+
"train_steps_per_second": 0.385
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 145,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6896551724137931,
|
13 |
+
"eval_loss": 21.915563583374023,
|
14 |
+
"eval_runtime": 125.1523,
|
15 |
+
"eval_samples_per_second": 19.304,
|
16 |
+
"eval_steps_per_second": 2.413,
|
17 |
+
"eval_wer": 1.0006400787789267,
|
18 |
+
"step": 100
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.0,
|
22 |
+
"step": 145,
|
23 |
+
"total_flos": 6.105598680744346e+17,
|
24 |
+
"train_loss": 18.517574757543102,
|
25 |
+
"train_runtime": 376.588,
|
26 |
+
"train_samples_per_second": 12.295,
|
27 |
+
"train_steps_per_second": 0.385
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 145,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 1,
|
34 |
+
"save_steps": 400,
|
35 |
+
"stateful_callbacks": {
|
36 |
+
"TrainerControl": {
|
37 |
+
"args": {
|
38 |
+
"should_epoch_stop": false,
|
39 |
+
"should_evaluate": false,
|
40 |
+
"should_log": false,
|
41 |
+
"should_save": true,
|
42 |
+
"should_training_stop": true
|
43 |
+
},
|
44 |
+
"attributes": {}
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"total_flos": 6.105598680744346e+17,
|
48 |
+
"train_batch_size": 16,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": null
|
51 |
+
}
|