Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
Generated from Trainer
Instructions to use Jjzzzz/whisper-tiny-hi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jjzzzz/whisper-tiny-hi2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Jjzzzz/whisper-tiny-hi2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Jjzzzz/whisper-tiny-hi2") model = AutoModelForSpeechSeq2Seq.from_pretrained("Jjzzzz/whisper-tiny-hi2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
base_model: openai/whisper-tiny
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: whisper-tiny-hi2
|
| 8 |
results: []
|
|
@@ -13,7 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# whisper-tiny-hi2
|
| 15 |
|
| 16 |
-
This model
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- wer
|
| 6 |
model-index:
|
| 7 |
- name: whisper-tiny-hi2
|
| 8 |
results: []
|
|
|
|
| 13 |
|
| 14 |
# whisper-tiny-hi2
|
| 15 |
|
| 16 |
+
This model was trained from scratch on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 3.6971
|
| 19 |
+
- Wer: 141.9341
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./whisper-tiny-hi-checkpoint-1",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"apply_spec_augment": false,
|
runs/Jun03_10-27-58_bharatsahaiyak-test/events.out.tfevents.1717410479.bharatsahaiyak-test.3254123.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f86fb1710cd891d76a7bc53776a78574a8b75f364afb736ee7648aeb9ed26272
|
| 3 |
+
size 6002
|
runs/Jun03_10-27-58_bharatsahaiyak-test/events.out.tfevents.1717410894.bharatsahaiyak-test.3254123.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3da480bf941e8b92807383ffba6ac1d4dd9f4df614a02b73ca26ecaeb3dc7800
|
| 3 |
+
size 400
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e98cc65972bc067fc69d6070fcb01a9c64680d57dc1b6eab7f5d45166430e8e9
|
| 3 |
size 5240
|