Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use fsicoli/whisper-medium-pt-cv19-fleurs2-lr-wu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fsicoli/whisper-medium-pt-cv19-fleurs2-lr-wu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="fsicoli/whisper-medium-pt-cv19-fleurs2-lr-wu")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("fsicoli/whisper-medium-pt-cv19-fleurs2-lr-wu") model = AutoModelForSpeechSeq2Seq.from_pretrained("fsicoli/whisper-medium-pt-cv19-fleurs2-lr-wu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- README.md +17 -4
- all_results.json +15 -0
- eval_results.json +9 -0
- runs/Sep21_23-25-55_DITEC2014063010/events.out.tfevents.1727163073.DITEC2014063010 +3 -0
- train_results.json +9 -0
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -4,11 +4,24 @@ license: apache-2.0
|
|
| 4 |
base_model: openai/whisper-medium
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
- name: whisper-medium-pt-cv19-fleurs2-lr-wu
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# whisper-medium-pt-cv19-fleurs2-lr-wu
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Wer: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 4 |
base_model: openai/whisper-medium
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- fsicoli/cv19-fleurs
|
| 9 |
metrics:
|
| 10 |
- wer
|
| 11 |
model-index:
|
| 12 |
- name: whisper-medium-pt-cv19-fleurs2-lr-wu
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Automatic Speech Recognition
|
| 16 |
+
type: automatic-speech-recognition
|
| 17 |
+
dataset:
|
| 18 |
+
name: fsicoli/cv19-fleurs default
|
| 19 |
+
type: fsicoli/cv19-fleurs
|
| 20 |
+
args: default
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 0.10248288219107954
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 29 |
|
| 30 |
# whisper-medium-pt-cv19-fleurs2-lr-wu
|
| 31 |
|
| 32 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the fsicoli/cv19-fleurs default dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.1694
|
| 35 |
+
- Wer: 0.1025
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.441647597254004,
|
| 3 |
+
"eval_loss": 0.16944891214370728,
|
| 4 |
+
"eval_runtime": 5188.5647,
|
| 5 |
+
"eval_samples": 9522,
|
| 6 |
+
"eval_samples_per_second": 1.835,
|
| 7 |
+
"eval_steps_per_second": 0.23,
|
| 8 |
+
"eval_wer": 0.10248288219107954,
|
| 9 |
+
"total_flos": 4.081970563920691e+20,
|
| 10 |
+
"train_loss": 0.03853472162485123,
|
| 11 |
+
"train_runtime": 185796.3327,
|
| 12 |
+
"train_samples": 34956,
|
| 13 |
+
"train_samples_per_second": 2.153,
|
| 14 |
+
"train_steps_per_second": 0.135
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.441647597254004,
|
| 3 |
+
"eval_loss": 0.16944891214370728,
|
| 4 |
+
"eval_runtime": 5188.5647,
|
| 5 |
+
"eval_samples": 9522,
|
| 6 |
+
"eval_samples_per_second": 1.835,
|
| 7 |
+
"eval_steps_per_second": 0.23,
|
| 8 |
+
"eval_wer": 0.10248288219107954
|
| 9 |
+
}
|
runs/Sep21_23-25-55_DITEC2014063010/events.out.tfevents.1727163073.DITEC2014063010
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4e38f1cfdae60c6624a670265cbceeb0a2139eda0f3cdcddbeba19fcb4e21af
|
| 3 |
+
size 40
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 11.441647597254004,
|
| 3 |
+
"total_flos": 4.081970563920691e+20,
|
| 4 |
+
"train_loss": 0.03853472162485123,
|
| 5 |
+
"train_runtime": 185796.3327,
|
| 6 |
+
"train_samples": 34956,
|
| 7 |
+
"train_samples_per_second": 2.153,
|
| 8 |
+
"train_steps_per_second": 0.135
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|