Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,9 @@ tags:
|
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_11_0
|
|
|
|
|
|
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
@@ -31,12 +34,27 @@ model-index:
|
|
31 |
dataset:
|
32 |
name: FLEURS ASR
|
33 |
type: google/fleurs
|
|
|
34 |
split: test
|
35 |
-
args:
|
36 |
metrics:
|
37 |
- name: WER
|
38 |
type: wer
|
39 |
value: 4.03
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
---
|
41 |
|
42 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -53,12 +71,15 @@ Using the script provided in the Whisper Sprint (Dec. 2022) the models achieves
|
|
53 |
|
54 |
- **google/fleurs: 4.03 %**
|
55 |
(python [run_eval_whisper_streaming.py](https://github.com/huggingface/community-events/blob/main/whisper-fine-tuning-event/run_eval_whisper_streaming.py) --model_id="deepdml/whisper-medium-mix-es" --dataset="google/fleurs" --config="es_419" --device=0 --language="es")
|
56 |
-
- mozilla-foundation/common_voice_11_0: Calculating...
|
57 |
|
58 |
-
- **facebook/multilingual_librispeech:
|
|
|
59 |
|
60 |
- **facebook/voxpopuli: 8.37 %**
|
61 |
-
(
|
|
|
|
|
|
|
62 |
|
63 |
|
64 |
## Model description
|
|
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_11_0
|
10 |
+
- google/fleurs
|
11 |
+
- facebook/multilingual_librispeech
|
12 |
+
- facebook/voxpopuli
|
13 |
metrics:
|
14 |
- wer
|
15 |
model-index:
|
|
|
34 |
dataset:
|
35 |
name: FLEURS ASR
|
36 |
type: google/fleurs
|
37 |
+
config: es_419
|
38 |
split: test
|
39 |
+
args: es
|
40 |
metrics:
|
41 |
- name: WER
|
42 |
type: wer
|
43 |
value: 4.03
|
44 |
+
- task:
|
45 |
+
name: Automatic Speech Recognition
|
46 |
+
type: automatic-speech-recognition
|
47 |
+
dataset:
|
48 |
+
name: Multilingual LibriSpeech
|
49 |
+
type: facebook/multilingual_librispeech
|
50 |
+
config: spanish
|
51 |
+
split: test
|
52 |
+
args:
|
53 |
+
language: es
|
54 |
+
metrics:
|
55 |
+
- name: WER
|
56 |
+
type: wer
|
57 |
+
value: 4.66
|
58 |
---
|
59 |
|
60 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
71 |
|
72 |
- **google/fleurs: 4.03 %**
|
73 |
(python [run_eval_whisper_streaming.py](https://github.com/huggingface/community-events/blob/main/whisper-fine-tuning-event/run_eval_whisper_streaming.py) --model_id="deepdml/whisper-medium-mix-es" --dataset="google/fleurs" --config="es_419" --device=0 --language="es")
|
|
|
74 |
|
75 |
+
- **facebook/multilingual_librispeech: 4.66 %**
|
76 |
+
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="facebook/multilingual_librispeech" --config="spanish" --device=0 --language="es")
|
77 |
|
78 |
- **facebook/voxpopuli: 8.37 %**
|
79 |
+
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="facebook/voxpopuli" --config="es" --device=0 --language="es")
|
80 |
+
|
81 |
+
- **mozilla-foundation/common_voice_11_0: Calculating...**
|
82 |
+
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="mozilla-foundation/common_voice_11_0" --config="es" --device=0 --language="es")
|
83 |
|
84 |
|
85 |
## Model description
|