Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Basque
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use zuazo/whisper-medium-eu-cv21.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zuazo/whisper-medium-eu-cv21.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="zuazo/whisper-medium-eu-cv21.0")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("zuazo/whisper-medium-eu-cv21.0") model = AutoModelForSpeechSeq2Seq.from_pretrained("zuazo/whisper-medium-eu-cv21.0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -1,22 +1,25 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: openai/whisper-medium
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
-
-
|
| 9 |
metrics:
|
| 10 |
- wer
|
| 11 |
model-index:
|
| 12 |
-
- name:
|
| 13 |
results:
|
| 14 |
- task:
|
| 15 |
name: Automatic Speech Recognition
|
| 16 |
type: automatic-speech-recognition
|
| 17 |
dataset:
|
| 18 |
-
name:
|
| 19 |
-
type:
|
| 20 |
config: default
|
| 21 |
split: test
|
| 22 |
args: default
|
|
@@ -29,9 +32,9 @@ model-index:
|
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
|
| 32 |
-
#
|
| 33 |
|
| 34 |
-
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
- Loss: 0.3958
|
| 37 |
- Wer: 8.3789
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
language:
|
| 4 |
+
- eu
|
| 5 |
license: apache-2.0
|
| 6 |
base_model: openai/whisper-medium
|
| 7 |
tags:
|
| 8 |
+
- whisper-event
|
| 9 |
- generated_from_trainer
|
| 10 |
datasets:
|
| 11 |
+
- common_voice_21_0_eu
|
| 12 |
metrics:
|
| 13 |
- wer
|
| 14 |
model-index:
|
| 15 |
+
- name: Whisper Medium Basque
|
| 16 |
results:
|
| 17 |
- task:
|
| 18 |
name: Automatic Speech Recognition
|
| 19 |
type: automatic-speech-recognition
|
| 20 |
dataset:
|
| 21 |
+
name: common_voice_21_0_eu
|
| 22 |
+
type: common_voice_21_0_eu
|
| 23 |
config: default
|
| 24 |
split: test
|
| 25 |
args: default
|
|
|
|
| 32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 33 |
should probably proofread and complete it, then remove this comment. -->
|
| 34 |
|
| 35 |
+
# Whisper Medium Basque
|
| 36 |
|
| 37 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the common_voice_21_0_eu dataset.
|
| 38 |
It achieves the following results on the evaluation set:
|
| 39 |
- Loss: 0.3958
|
| 40 |
- Wer: 8.3789
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 222.22222222222223,
|
| 3 |
+
"eval_loss": 0.3958326578140259,
|
| 4 |
+
"eval_runtime": 796.6584,
|
| 5 |
+
"eval_samples_per_second": 18.054,
|
| 6 |
+
"eval_steps_per_second": 0.565,
|
| 7 |
+
"eval_wer": 8.378851722762663,
|
| 8 |
+
"total_flos": 6.524167882286039e+21,
|
| 9 |
+
"train_loss": 0.005228559886442444,
|
| 10 |
+
"train_runtime": 169694.5318,
|
| 11 |
+
"train_samples_per_second": 37.715,
|
| 12 |
+
"train_steps_per_second": 0.589
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 222.22222222222223,
|
| 3 |
+
"eval_loss": 0.3958326578140259,
|
| 4 |
+
"eval_runtime": 796.6584,
|
| 5 |
+
"eval_samples_per_second": 18.054,
|
| 6 |
+
"eval_steps_per_second": 0.565,
|
| 7 |
+
"eval_wer": 8.378851722762663
|
| 8 |
+
}
|
runs/Jun05_23-00-00_nej80nv-01113.itbatera.euskadi.eus/events.out.tfevents.1749327878.nej80nv-01113.itbatera.euskadi.eus
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f722efe1dd7be58d0918614c0e379e8b75684cf6b3d2cf8ba6b4209ab443bb9
|
| 3 |
+
size 40
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 222.22222222222223,
|
| 3 |
+
"total_flos": 6.524167882286039e+21,
|
| 4 |
+
"train_loss": 0.005228559886442444,
|
| 5 |
+
"train_runtime": 169694.5318,
|
| 6 |
+
"train_samples_per_second": 37.715,
|
| 7 |
+
"train_steps_per_second": 0.589
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|