Automatic Speech Recognition
Transformers
Safetensors
Arabic
English
cohere_asr
arabic
code-switching
decoder-only-finetune
Instructions to use nsa01n/cohere-cs-decoder-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nsa01n/cohere-cs-decoder-full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nsa01n/cohere-cs-decoder-full")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nsa01n/cohere-cs-decoder-full") model = AutoModelForSpeechSeq2Seq.from_pretrained("nsa01n/cohere-cs-decoder-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
decoder-only fine-tune (full)
Browse files- model.safetensors +1 -1
- train_meta.json +9 -9
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4131809192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ad672142f31fa94145e4241260b5221c9e4c40139707c77d2982922cc96668
|
| 3 |
size 4131809192
|
train_meta.json
CHANGED
|
@@ -7,15 +7,15 @@
|
|
| 7 |
"effective_batch_size": 32,
|
| 8 |
"seed": 42,
|
| 9 |
"bf16": true,
|
| 10 |
-
"train_examples":
|
| 11 |
"val_examples": 454,
|
| 12 |
"metrics": {
|
| 13 |
-
"train_runtime":
|
| 14 |
-
"train_samples_per_second":
|
| 15 |
-
"train_steps_per_second": 0.
|
| 16 |
-
"total_flos":
|
| 17 |
-
"train_loss": 0.
|
| 18 |
-
"epoch":
|
| 19 |
},
|
| 20 |
"freeze": {
|
| 21 |
"variant": "full",
|
|
@@ -42,8 +42,8 @@
|
|
| 42 |
"trainable_pct": 8.245
|
| 43 |
},
|
| 44 |
"hyperparameters": {
|
| 45 |
-
"learning_rate":
|
| 46 |
-
"num_train_epochs":
|
| 47 |
"lr_scheduler_type": "cosine",
|
| 48 |
"warmup_ratio": 0.03,
|
| 49 |
"per_device_train_batch_size": 16,
|
|
|
|
| 7 |
"effective_batch_size": 32,
|
| 8 |
"seed": 42,
|
| 9 |
"bf16": true,
|
| 10 |
+
"train_examples": 1900,
|
| 11 |
"val_examples": 454,
|
| 12 |
"metrics": {
|
| 13 |
+
"train_runtime": 419.5181,
|
| 14 |
+
"train_samples_per_second": 27.174,
|
| 15 |
+
"train_steps_per_second": 0.858,
|
| 16 |
+
"total_flos": 5.372639220298678e+19,
|
| 17 |
+
"train_loss": 0.10716057336992688,
|
| 18 |
+
"epoch": 6.0
|
| 19 |
},
|
| 20 |
"freeze": {
|
| 21 |
"variant": "full",
|
|
|
|
| 42 |
"trainable_pct": 8.245
|
| 43 |
},
|
| 44 |
"hyperparameters": {
|
| 45 |
+
"learning_rate": 8e-05,
|
| 46 |
+
"num_train_epochs": 6,
|
| 47 |
"lr_scheduler_type": "cosine",
|
| 48 |
"warmup_ratio": 0.03,
|
| 49 |
"per_device_train_batch_size": 16,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5393
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a929bfae0de227585524b266ca694feddebaa7cd08d324f5b832ed0601a12e1
|
| 3 |
size 5393
|