whisper-large-v2-multiple-17
Browse files- README.md +41 -179
- generation_config.json +228 -0
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -1,199 +1,61 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
-
|
|
|
7 |
|
8 |
-
|
9 |
|
|
|
|
|
|
|
10 |
|
|
|
11 |
|
12 |
-
|
13 |
|
14 |
-
|
15 |
|
16 |
-
|
17 |
|
18 |
-
|
19 |
|
20 |
-
|
21 |
-
- **Funded by [optional]:** [More Information Needed]
|
22 |
-
- **Shared by [optional]:** [More Information Needed]
|
23 |
-
- **Model type:** [More Information Needed]
|
24 |
-
- **Language(s) (NLP):** [More Information Needed]
|
25 |
-
- **License:** [More Information Needed]
|
26 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
|
28 |
-
|
29 |
|
30 |
-
|
31 |
|
32 |
-
|
33 |
-
-
|
34 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
-
|
37 |
|
38 |
-
|
|
|
|
|
|
|
39 |
|
40 |
-
### Direct Use
|
41 |
|
42 |
-
|
43 |
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
-
|
50 |
-
[More Information Needed]
|
51 |
-
|
52 |
-
### Out-of-Scope Use
|
53 |
-
|
54 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
-
|
56 |
-
[More Information Needed]
|
57 |
-
|
58 |
-
## Bias, Risks, and Limitations
|
59 |
-
|
60 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
-
|
62 |
-
[More Information Needed]
|
63 |
-
|
64 |
-
### Recommendations
|
65 |
-
|
66 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
-
|
68 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
-
|
70 |
-
## How to Get Started with the Model
|
71 |
-
|
72 |
-
Use the code below to get started with the model.
|
73 |
-
|
74 |
-
[More Information Needed]
|
75 |
-
|
76 |
-
## Training Details
|
77 |
-
|
78 |
-
### Training Data
|
79 |
-
|
80 |
-
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
-
|
82 |
-
[More Information Needed]
|
83 |
-
|
84 |
-
### Training Procedure
|
85 |
-
|
86 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
-
|
88 |
-
#### Preprocessing [optional]
|
89 |
-
|
90 |
-
[More Information Needed]
|
91 |
-
|
92 |
-
|
93 |
-
#### Training Hyperparameters
|
94 |
-
|
95 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
-
|
97 |
-
#### Speeds, Sizes, Times [optional]
|
98 |
-
|
99 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
-
|
101 |
-
[More Information Needed]
|
102 |
-
|
103 |
-
## Evaluation
|
104 |
-
|
105 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
-
|
107 |
-
### Testing Data, Factors & Metrics
|
108 |
-
|
109 |
-
#### Testing Data
|
110 |
-
|
111 |
-
<!-- This should link to a Dataset Card if possible. -->
|
112 |
-
|
113 |
-
[More Information Needed]
|
114 |
-
|
115 |
-
#### Factors
|
116 |
-
|
117 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
-
|
119 |
-
[More Information Needed]
|
120 |
-
|
121 |
-
#### Metrics
|
122 |
-
|
123 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
-
|
125 |
-
[More Information Needed]
|
126 |
-
|
127 |
-
### Results
|
128 |
-
|
129 |
-
[More Information Needed]
|
130 |
-
|
131 |
-
#### Summary
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
## Model Examination [optional]
|
136 |
-
|
137 |
-
<!-- Relevant interpretability work for the model goes here -->
|
138 |
-
|
139 |
-
[More Information Needed]
|
140 |
-
|
141 |
-
## Environmental Impact
|
142 |
-
|
143 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
-
|
145 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
-
|
147 |
-
- **Hardware Type:** [More Information Needed]
|
148 |
-
- **Hours used:** [More Information Needed]
|
149 |
-
- **Cloud Provider:** [More Information Needed]
|
150 |
-
- **Compute Region:** [More Information Needed]
|
151 |
-
- **Carbon Emitted:** [More Information Needed]
|
152 |
-
|
153 |
-
## Technical Specifications [optional]
|
154 |
-
|
155 |
-
### Model Architecture and Objective
|
156 |
-
|
157 |
-
[More Information Needed]
|
158 |
-
|
159 |
-
### Compute Infrastructure
|
160 |
-
|
161 |
-
[More Information Needed]
|
162 |
-
|
163 |
-
#### Hardware
|
164 |
-
|
165 |
-
[More Information Needed]
|
166 |
-
|
167 |
-
#### Software
|
168 |
-
|
169 |
-
[More Information Needed]
|
170 |
-
|
171 |
-
## Citation [optional]
|
172 |
-
|
173 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
-
|
175 |
-
**BibTeX:**
|
176 |
-
|
177 |
-
[More Information Needed]
|
178 |
-
|
179 |
-
**APA:**
|
180 |
-
|
181 |
-
[More Information Needed]
|
182 |
-
|
183 |
-
## Glossary [optional]
|
184 |
-
|
185 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## More Information [optional]
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
## Model Card Authors [optional]
|
194 |
-
|
195 |
-
[More Information Needed]
|
196 |
-
|
197 |
-
## Model Card Contact
|
198 |
-
|
199 |
-
[More Information Needed]
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: openai/whisper-large-v2
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: whisper-large-v2-multiple-17
|
9 |
+
results: []
|
10 |
---
|
11 |
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
|
15 |
+
# whisper-large-v2-multiple-17
|
16 |
|
17 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1525
|
20 |
|
21 |
+
## Model description
|
22 |
|
23 |
+
More information needed
|
24 |
|
25 |
+
## Intended uses & limitations
|
26 |
|
27 |
+
More information needed
|
28 |
|
29 |
+
## Training and evaluation data
|
30 |
|
31 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
33 |
+
## Training procedure
|
34 |
|
35 |
+
### Training hyperparameters
|
36 |
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 1e-05
|
39 |
+
- train_batch_size: 64
|
40 |
+
- eval_batch_size: 64
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_ratio: 0.1
|
45 |
+
- num_epochs: 3
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
|
48 |
+
### Training results
|
49 |
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:------:|:----:|:---------------:|
|
52 |
+
| 0.1221 | 1.1779 | 1000 | 0.1495 |
|
53 |
+
| 0.057 | 2.3557 | 2000 | 0.1525 |
|
54 |
|
|
|
55 |
|
56 |
+
### Framework versions
|
57 |
|
58 |
+
- Transformers 4.45.2
|
59 |
+
- Pytorch 2.4.0+cu121
|
60 |
+
- Datasets 2.18.0
|
61 |
+
- Tokenizers 0.20.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
generation_config.json
ADDED
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
10,
|
5 |
+
12
|
6 |
+
],
|
7 |
+
[
|
8 |
+
13,
|
9 |
+
17
|
10 |
+
],
|
11 |
+
[
|
12 |
+
16,
|
13 |
+
11
|
14 |
+
],
|
15 |
+
[
|
16 |
+
16,
|
17 |
+
12
|
18 |
+
],
|
19 |
+
[
|
20 |
+
16,
|
21 |
+
13
|
22 |
+
],
|
23 |
+
[
|
24 |
+
17,
|
25 |
+
15
|
26 |
+
],
|
27 |
+
[
|
28 |
+
17,
|
29 |
+
16
|
30 |
+
],
|
31 |
+
[
|
32 |
+
18,
|
33 |
+
4
|
34 |
+
],
|
35 |
+
[
|
36 |
+
18,
|
37 |
+
11
|
38 |
+
],
|
39 |
+
[
|
40 |
+
18,
|
41 |
+
19
|
42 |
+
],
|
43 |
+
[
|
44 |
+
19,
|
45 |
+
11
|
46 |
+
],
|
47 |
+
[
|
48 |
+
21,
|
49 |
+
2
|
50 |
+
],
|
51 |
+
[
|
52 |
+
21,
|
53 |
+
3
|
54 |
+
],
|
55 |
+
[
|
56 |
+
22,
|
57 |
+
3
|
58 |
+
],
|
59 |
+
[
|
60 |
+
22,
|
61 |
+
9
|
62 |
+
],
|
63 |
+
[
|
64 |
+
22,
|
65 |
+
12
|
66 |
+
],
|
67 |
+
[
|
68 |
+
23,
|
69 |
+
5
|
70 |
+
],
|
71 |
+
[
|
72 |
+
23,
|
73 |
+
7
|
74 |
+
],
|
75 |
+
[
|
76 |
+
23,
|
77 |
+
13
|
78 |
+
],
|
79 |
+
[
|
80 |
+
25,
|
81 |
+
5
|
82 |
+
],
|
83 |
+
[
|
84 |
+
26,
|
85 |
+
1
|
86 |
+
],
|
87 |
+
[
|
88 |
+
26,
|
89 |
+
12
|
90 |
+
],
|
91 |
+
[
|
92 |
+
27,
|
93 |
+
15
|
94 |
+
]
|
95 |
+
],
|
96 |
+
"begin_suppress_tokens": [
|
97 |
+
220,
|
98 |
+
50257
|
99 |
+
],
|
100 |
+
"bos_token_id": 50257,
|
101 |
+
"decoder_start_token_id": 50258,
|
102 |
+
"eos_token_id": 50257,
|
103 |
+
"forced_decoder_ids": [
|
104 |
+
[
|
105 |
+
1,
|
106 |
+
null
|
107 |
+
],
|
108 |
+
[
|
109 |
+
2,
|
110 |
+
50359
|
111 |
+
]
|
112 |
+
],
|
113 |
+
"is_multilingual": true,
|
114 |
+
"lang_to_id": {
|
115 |
+
"<|af|>": 50327,
|
116 |
+
"<|am|>": 50334,
|
117 |
+
"<|ar|>": 50272,
|
118 |
+
"<|as|>": 50350,
|
119 |
+
"<|az|>": 50304,
|
120 |
+
"<|ba|>": 50355,
|
121 |
+
"<|be|>": 50330,
|
122 |
+
"<|bg|>": 50292,
|
123 |
+
"<|bn|>": 50302,
|
124 |
+
"<|bo|>": 50347,
|
125 |
+
"<|br|>": 50309,
|
126 |
+
"<|bs|>": 50315,
|
127 |
+
"<|ca|>": 50270,
|
128 |
+
"<|cs|>": 50283,
|
129 |
+
"<|cy|>": 50297,
|
130 |
+
"<|da|>": 50285,
|
131 |
+
"<|de|>": 50261,
|
132 |
+
"<|el|>": 50281,
|
133 |
+
"<|en|>": 50259,
|
134 |
+
"<|es|>": 50262,
|
135 |
+
"<|et|>": 50307,
|
136 |
+
"<|eu|>": 50310,
|
137 |
+
"<|fa|>": 50300,
|
138 |
+
"<|fi|>": 50277,
|
139 |
+
"<|fo|>": 50338,
|
140 |
+
"<|fr|>": 50265,
|
141 |
+
"<|gl|>": 50319,
|
142 |
+
"<|gu|>": 50333,
|
143 |
+
"<|haw|>": 50352,
|
144 |
+
"<|ha|>": 50354,
|
145 |
+
"<|he|>": 50279,
|
146 |
+
"<|hi|>": 50276,
|
147 |
+
"<|hr|>": 50291,
|
148 |
+
"<|ht|>": 50339,
|
149 |
+
"<|hu|>": 50286,
|
150 |
+
"<|hy|>": 50312,
|
151 |
+
"<|id|>": 50275,
|
152 |
+
"<|is|>": 50311,
|
153 |
+
"<|it|>": 50274,
|
154 |
+
"<|ja|>": 50266,
|
155 |
+
"<|jw|>": 50356,
|
156 |
+
"<|ka|>": 50329,
|
157 |
+
"<|kk|>": 50316,
|
158 |
+
"<|km|>": 50323,
|
159 |
+
"<|kn|>": 50306,
|
160 |
+
"<|ko|>": 50264,
|
161 |
+
"<|la|>": 50294,
|
162 |
+
"<|lb|>": 50345,
|
163 |
+
"<|ln|>": 50353,
|
164 |
+
"<|lo|>": 50336,
|
165 |
+
"<|lt|>": 50293,
|
166 |
+
"<|lv|>": 50301,
|
167 |
+
"<|mg|>": 50349,
|
168 |
+
"<|mi|>": 50295,
|
169 |
+
"<|mk|>": 50308,
|
170 |
+
"<|ml|>": 50296,
|
171 |
+
"<|mn|>": 50314,
|
172 |
+
"<|mr|>": 50320,
|
173 |
+
"<|ms|>": 50282,
|
174 |
+
"<|mt|>": 50343,
|
175 |
+
"<|my|>": 50346,
|
176 |
+
"<|ne|>": 50313,
|
177 |
+
"<|nl|>": 50271,
|
178 |
+
"<|nn|>": 50342,
|
179 |
+
"<|no|>": 50288,
|
180 |
+
"<|oc|>": 50328,
|
181 |
+
"<|pa|>": 50321,
|
182 |
+
"<|pl|>": 50269,
|
183 |
+
"<|ps|>": 50340,
|
184 |
+
"<|pt|>": 50267,
|
185 |
+
"<|ro|>": 50284,
|
186 |
+
"<|ru|>": 50263,
|
187 |
+
"<|sa|>": 50344,
|
188 |
+
"<|sd|>": 50332,
|
189 |
+
"<|si|>": 50322,
|
190 |
+
"<|sk|>": 50298,
|
191 |
+
"<|sl|>": 50305,
|
192 |
+
"<|sn|>": 50324,
|
193 |
+
"<|so|>": 50326,
|
194 |
+
"<|sq|>": 50317,
|
195 |
+
"<|sr|>": 50303,
|
196 |
+
"<|su|>": 50357,
|
197 |
+
"<|sv|>": 50273,
|
198 |
+
"<|sw|>": 50318,
|
199 |
+
"<|ta|>": 50287,
|
200 |
+
"<|te|>": 50299,
|
201 |
+
"<|tg|>": 50331,
|
202 |
+
"<|th|>": 50289,
|
203 |
+
"<|tk|>": 50341,
|
204 |
+
"<|tl|>": 50348,
|
205 |
+
"<|tr|>": 50268,
|
206 |
+
"<|tt|>": 50351,
|
207 |
+
"<|uk|>": 50280,
|
208 |
+
"<|ur|>": 50290,
|
209 |
+
"<|uz|>": 50337,
|
210 |
+
"<|vi|>": 50278,
|
211 |
+
"<|yi|>": 50335,
|
212 |
+
"<|yo|>": 50325,
|
213 |
+
"<|zh|>": 50260
|
214 |
+
},
|
215 |
+
"language": "tr",
|
216 |
+
"max_initial_timestamp_index": 50,
|
217 |
+
"max_length": 448,
|
218 |
+
"no_timestamps_token_id": 50363,
|
219 |
+
"pad_token_id": 50257,
|
220 |
+
"prev_sot_token_id": 50361,
|
221 |
+
"return_timestamps": false,
|
222 |
+
"suppress_tokens": [],
|
223 |
+
"task_to_id": {
|
224 |
+
"transcribe": 50359,
|
225 |
+
"translate": 50358
|
226 |
+
},
|
227 |
+
"transformers_version": "4.45.2"
|
228 |
+
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4992706480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:975b1ecce9dd4c5d13df47be636f7cae4bbac4b9f561b7a8300e474bab6e0829
|
3 |
size 4992706480
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54b035d8d0f129629d29c3af84613f68a29ab3bb7c782d12a86820ff06f37e31
|
3 |
size 1180663192
|