waveletdeboshir
commited on
Commit
•
1041e65
1
Parent(s):
9396234
Upload WhisperForConditionalGeneration
Browse files- README.md +185 -134
- config.json +64 -0
- generation_config.json +160 -0
- model.safetensors +3 -0
README.md
CHANGED
@@ -1,148 +1,199 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
library_name: transformers
|
4 |
-
|
5 |
-
tags:
|
6 |
-
- asr
|
7 |
-
- Pytorch
|
8 |
-
- pruned
|
9 |
-
- audio
|
10 |
-
- automatic-speech-recognition
|
11 |
-
language:
|
12 |
-
- en
|
13 |
-
- zh
|
14 |
-
- de
|
15 |
-
- es
|
16 |
-
- ru
|
17 |
-
- ko
|
18 |
-
- fr
|
19 |
-
- ja
|
20 |
-
- pt
|
21 |
-
- tr
|
22 |
-
- pl
|
23 |
-
- ca
|
24 |
-
- nl
|
25 |
-
- ar
|
26 |
-
- sv
|
27 |
-
- it
|
28 |
-
- id
|
29 |
-
- hi
|
30 |
-
- fi
|
31 |
-
- vi
|
32 |
-
- he
|
33 |
-
- uk
|
34 |
-
- el
|
35 |
-
- ms
|
36 |
-
- cs
|
37 |
-
- ro
|
38 |
-
- da
|
39 |
-
- hu
|
40 |
-
- ta
|
41 |
-
- 'no'
|
42 |
-
- th
|
43 |
-
- ur
|
44 |
-
- hr
|
45 |
-
- bg
|
46 |
-
- lt
|
47 |
-
- la
|
48 |
-
- mi
|
49 |
-
- ml
|
50 |
-
- cy
|
51 |
-
- sk
|
52 |
-
- te
|
53 |
-
- fa
|
54 |
-
- lv
|
55 |
-
- bn
|
56 |
-
- sr
|
57 |
-
- az
|
58 |
-
- sl
|
59 |
-
- kn
|
60 |
-
- et
|
61 |
-
- mk
|
62 |
-
- br
|
63 |
-
- eu
|
64 |
-
- is
|
65 |
-
- hy
|
66 |
-
- ne
|
67 |
-
- mn
|
68 |
-
- bs
|
69 |
-
- kk
|
70 |
-
- sq
|
71 |
-
- sw
|
72 |
-
- gl
|
73 |
-
- mr
|
74 |
-
- pa
|
75 |
-
- si
|
76 |
-
- km
|
77 |
-
- sn
|
78 |
-
- yo
|
79 |
-
- so
|
80 |
-
- af
|
81 |
-
- oc
|
82 |
-
- ka
|
83 |
-
- be
|
84 |
-
- tg
|
85 |
-
- sd
|
86 |
-
- gu
|
87 |
-
- am
|
88 |
-
- yi
|
89 |
-
- lo
|
90 |
-
- uz
|
91 |
-
- fo
|
92 |
-
- ht
|
93 |
-
- ps
|
94 |
-
- tk
|
95 |
-
- nn
|
96 |
-
- mt
|
97 |
-
- sa
|
98 |
-
- lb
|
99 |
-
- my
|
100 |
-
- bo
|
101 |
-
- tl
|
102 |
-
- mg
|
103 |
-
- as
|
104 |
-
- tt
|
105 |
-
- haw
|
106 |
-
- ln
|
107 |
-
- ha
|
108 |
-
- ba
|
109 |
-
- jw
|
110 |
-
- su
|
111 |
-
base_model:
|
112 |
-
- openai/whisper-large-v3-turbo
|
113 |
---
|
114 |
|
115 |
-
#
|
116 |
|
117 |
-
|
118 |
-
This is a version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) model without number tokens (token ids corresponding to numbers are excluded).
|
119 |
-
NO fine-tuning was used.
|
120 |
|
121 |
-
Phrases with spoken numbers will be transcribed with numbers as words.
|
122 |
|
123 |
-
Example: Instead of "25" this model will transcribe phrase as "twenty five".
|
124 |
|
125 |
-
##
|
126 |
-
Model can be used as an original whisper:
|
127 |
|
128 |
-
|
129 |
-
>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
|
130 |
-
>>> import torchaudio
|
131 |
|
132 |
-
|
133 |
-
>>> wav, sr = torchaudio.load("audio.wav")
|
134 |
|
135 |
-
|
136 |
-
>>> processor = WhisperProcessor.from_pretrained("waveletdeboshir/whisper-large-v3-turbo-no-numbers")
|
137 |
-
>>> model = WhisperForConditionalGeneration.from_pretrained("waveletdeboshir/whisper-large-v3-turbo-no-numbers")
|
138 |
|
139 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
|
141 |
-
|
142 |
-
>>> predicted_ids = model.generate(input_features)
|
143 |
-
>>> # decode token ids to text
|
144 |
-
>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
|
145 |
-
["<|startoftranscript|><|en|><|transcribe|><|notimestamps|> Twenty seven years. <|endoftext|>"]
|
146 |
|
147 |
-
|
148 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
2 |
library_name: transformers
|
3 |
+
tags: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
+
# Model Card for Model ID
|
7 |
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
|
|
|
|
9 |
|
|
|
10 |
|
|
|
11 |
|
12 |
+
## Model Details
|
|
|
13 |
|
14 |
+
### Model Description
|
|
|
|
|
15 |
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
|
|
17 |
|
18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
|
|
|
|
19 |
|
20 |
+
- **Developed by:** [More Information Needed]
|
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 |
+
### Model Sources [optional]
|
|
|
|
|
|
|
|
|
29 |
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
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]
|
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./models/whisper-large-v3-turbo-no-numbers",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
210,
|
12 |
+
49838
|
13 |
+
],
|
14 |
+
"bos_token_id": 49839,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 1280,
|
17 |
+
"decoder_attention_heads": 20,
|
18 |
+
"decoder_ffn_dim": 5120,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 4,
|
21 |
+
"decoder_start_token_id": 49840,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 20,
|
24 |
+
"encoder_ffn_dim": 5120,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 32,
|
27 |
+
"eos_token_id": 49839,
|
28 |
+
"forced_decoder_ids": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
49841
|
32 |
+
],
|
33 |
+
[
|
34 |
+
2,
|
35 |
+
49941
|
36 |
+
],
|
37 |
+
[
|
38 |
+
3,
|
39 |
+
49945
|
40 |
+
]
|
41 |
+
],
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"mask_feature_length": 10,
|
45 |
+
"mask_feature_min_masks": 0,
|
46 |
+
"mask_feature_prob": 0.0,
|
47 |
+
"mask_time_length": 10,
|
48 |
+
"mask_time_min_masks": 2,
|
49 |
+
"mask_time_prob": 0.05,
|
50 |
+
"max_source_positions": 1500,
|
51 |
+
"max_target_positions": 448,
|
52 |
+
"median_filter_width": 7,
|
53 |
+
"model_type": "whisper",
|
54 |
+
"num_hidden_layers": 32,
|
55 |
+
"num_mel_bins": 128,
|
56 |
+
"pad_token_id": 49839,
|
57 |
+
"scale_embedding": false,
|
58 |
+
"suppress_tokens": [],
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.44.0",
|
61 |
+
"use_cache": true,
|
62 |
+
"use_weighted_layer_sum": false,
|
63 |
+
"vocab_size": 51447
|
64 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
2,
|
5 |
+
4
|
6 |
+
],
|
7 |
+
[
|
8 |
+
2,
|
9 |
+
11
|
10 |
+
],
|
11 |
+
[
|
12 |
+
3,
|
13 |
+
3
|
14 |
+
],
|
15 |
+
[
|
16 |
+
3,
|
17 |
+
6
|
18 |
+
],
|
19 |
+
[
|
20 |
+
3,
|
21 |
+
11
|
22 |
+
],
|
23 |
+
[
|
24 |
+
3,
|
25 |
+
14
|
26 |
+
]
|
27 |
+
],
|
28 |
+
"begin_suppress_tokens": [
|
29 |
+
210,
|
30 |
+
49839
|
31 |
+
],
|
32 |
+
"bos_token_id": 49839,
|
33 |
+
"decoder_start_token_id": 49840,
|
34 |
+
"eos_token_id": 49839,
|
35 |
+
"forced_decoder_ids": [
|
36 |
+
[
|
37 |
+
1,
|
38 |
+
null
|
39 |
+
],
|
40 |
+
[
|
41 |
+
2,
|
42 |
+
49941
|
43 |
+
]
|
44 |
+
],
|
45 |
+
"is_multilingual": true,
|
46 |
+
"lang_to_id": {
|
47 |
+
"<|af|>": 49909,
|
48 |
+
"<|am|>": 49916,
|
49 |
+
"<|ar|>": 49854,
|
50 |
+
"<|as|>": 49932,
|
51 |
+
"<|az|>": 49886,
|
52 |
+
"<|ba|>": 49937,
|
53 |
+
"<|be|>": 49912,
|
54 |
+
"<|bg|>": 49874,
|
55 |
+
"<|bn|>": 49884,
|
56 |
+
"<|bo|>": 49929,
|
57 |
+
"<|br|>": 49891,
|
58 |
+
"<|bs|>": 49897,
|
59 |
+
"<|ca|>": 49852,
|
60 |
+
"<|cs|>": 49865,
|
61 |
+
"<|cy|>": 49879,
|
62 |
+
"<|da|>": 49867,
|
63 |
+
"<|de|>": 49843,
|
64 |
+
"<|el|>": 49863,
|
65 |
+
"<|en|>": 49841,
|
66 |
+
"<|es|>": 49844,
|
67 |
+
"<|et|>": 49889,
|
68 |
+
"<|eu|>": 49892,
|
69 |
+
"<|fa|>": 49882,
|
70 |
+
"<|fi|>": 49859,
|
71 |
+
"<|fo|>": 49920,
|
72 |
+
"<|fr|>": 49847,
|
73 |
+
"<|gl|>": 49901,
|
74 |
+
"<|gu|>": 49915,
|
75 |
+
"<|haw|>": 49934,
|
76 |
+
"<|ha|>": 49936,
|
77 |
+
"<|he|>": 49861,
|
78 |
+
"<|hi|>": 49858,
|
79 |
+
"<|hr|>": 49873,
|
80 |
+
"<|ht|>": 49921,
|
81 |
+
"<|hu|>": 49868,
|
82 |
+
"<|hy|>": 49894,
|
83 |
+
"<|id|>": 49857,
|
84 |
+
"<|is|>": 49893,
|
85 |
+
"<|it|>": 49856,
|
86 |
+
"<|ja|>": 49848,
|
87 |
+
"<|jw|>": 49938,
|
88 |
+
"<|ka|>": 49911,
|
89 |
+
"<|kk|>": 49898,
|
90 |
+
"<|km|>": 49905,
|
91 |
+
"<|kn|>": 49888,
|
92 |
+
"<|ko|>": 49846,
|
93 |
+
"<|la|>": 49876,
|
94 |
+
"<|lb|>": 49927,
|
95 |
+
"<|ln|>": 49935,
|
96 |
+
"<|lo|>": 49918,
|
97 |
+
"<|lt|>": 49875,
|
98 |
+
"<|lv|>": 49883,
|
99 |
+
"<|mg|>": 49931,
|
100 |
+
"<|mi|>": 49877,
|
101 |
+
"<|mk|>": 49890,
|
102 |
+
"<|ml|>": 49878,
|
103 |
+
"<|mn|>": 49896,
|
104 |
+
"<|mr|>": 49902,
|
105 |
+
"<|ms|>": 49864,
|
106 |
+
"<|mt|>": 49925,
|
107 |
+
"<|my|>": 49928,
|
108 |
+
"<|ne|>": 49895,
|
109 |
+
"<|nl|>": 49853,
|
110 |
+
"<|nn|>": 49924,
|
111 |
+
"<|no|>": 49870,
|
112 |
+
"<|oc|>": 49910,
|
113 |
+
"<|pa|>": 49903,
|
114 |
+
"<|pl|>": 49851,
|
115 |
+
"<|ps|>": 49922,
|
116 |
+
"<|pt|>": 49849,
|
117 |
+
"<|ro|>": 49866,
|
118 |
+
"<|ru|>": 49845,
|
119 |
+
"<|sa|>": 49926,
|
120 |
+
"<|sd|>": 49914,
|
121 |
+
"<|si|>": 49904,
|
122 |
+
"<|sk|>": 49880,
|
123 |
+
"<|sl|>": 49887,
|
124 |
+
"<|sn|>": 49906,
|
125 |
+
"<|so|>": 49908,
|
126 |
+
"<|sq|>": 49899,
|
127 |
+
"<|sr|>": 49885,
|
128 |
+
"<|su|>": 49939,
|
129 |
+
"<|sv|>": 49855,
|
130 |
+
"<|sw|>": 49900,
|
131 |
+
"<|ta|>": 49869,
|
132 |
+
"<|te|>": 49881,
|
133 |
+
"<|tg|>": 49913,
|
134 |
+
"<|th|>": 49871,
|
135 |
+
"<|tk|>": 49923,
|
136 |
+
"<|tl|>": 49930,
|
137 |
+
"<|tr|>": 49850,
|
138 |
+
"<|tt|>": 49933,
|
139 |
+
"<|uk|>": 49862,
|
140 |
+
"<|ur|>": 49872,
|
141 |
+
"<|uz|>": 49919,
|
142 |
+
"<|vi|>": 49860,
|
143 |
+
"<|yi|>": 49917,
|
144 |
+
"<|yo|>": 49907,
|
145 |
+
"<|yue|>": 49940,
|
146 |
+
"<|zh|>": 49842
|
147 |
+
},
|
148 |
+
"max_initial_timestamp_index": 50,
|
149 |
+
"max_length": 448,
|
150 |
+
"no_timestamps_token_id": 49946,
|
151 |
+
"pad_token_id": 49839,
|
152 |
+
"prev_sot_token_id": 49944,
|
153 |
+
"return_timestamps": false,
|
154 |
+
"suppress_tokens": [],
|
155 |
+
"task_to_id": {
|
156 |
+
"transcribe": 49942,
|
157 |
+
"translate": 49941
|
158 |
+
},
|
159 |
+
"transformers_version": "4.44.0"
|
160 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06c6a815adce9914b0cfe26a68d52d2e1ebb9e2ac1064d238cbbe270ced4c61b
|
3 |
+
size 3233436128
|