初始化项目，由ModelHub XC社区提供模型
Model: ayoubkirouane/whisper-small-ar Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
55
README.md
Normal file
55
README.md
Normal file
@@ -0,0 +1,55 @@
|
||||
---
|
||||
language:
|
||||
- ar
|
||||
license: apache-2.0
|
||||
base_model: openai/whisper-small
|
||||
datasets:
|
||||
- mozilla-foundation/common_voice_11_0
|
||||
model-index:
|
||||
- name: Whisper-small-ar
|
||||
results: []
|
||||
library_name: transformers
|
||||
pipeline_tag: automatic-speech-recognition
|
||||
---
|
||||
|
||||
# Arabic-Whisper Small
|
||||
|
||||
## Description
|
||||
|
||||
Whisper-small-ar is an Automatic Speech Recognition (ASR) model fine-tuned specifically for the Arabic language using the Whisper model architecture. ASR models are designed to convert spoken language into written text. This model has been fine-tuned on the Mozilla Common Voice dataset (version 11.0) to transcribe spoken Arabic speech into textual form.
|
||||
|
||||
### Key Features
|
||||
|
||||
- **Arabic Language Support:** Whisper-small-ar is optimized for recognizing and transcribing the Arabic language accurately. It can handle various Arabic dialects and accents.
|
||||
|
||||
- **Transformer Architecture:** The model is built on a powerful Transformer-based encoder-decoder architecture, which has demonstrated state-of-the-art performance in various natural language processing tasks, including ASR.
|
||||
|
||||
- **Fine-tuned for Arabic ASR:** The model has undergone a fine-tuning process on a substantial amount of Arabic speech data, making it well-suited for a wide range of ASR applications in Arabic, such as transcription of podcasts, call center recordings, and more.
|
||||
|
||||
- **Open-Source:** Whisper-small-ar is open-source and available for use by the research and developer community, facilitating the advancement of ASR technology for the Arabic language.
|
||||
|
||||
- **Compatible with Hugging Face Transformers:** You can easily integrate and utilize this model in your ASR projects using the Hugging Face Transformers library.
|
||||
|
||||
### Use Cases
|
||||
|
||||
Whisper-small-ar can be employed in a variety of ASR use cases, including:
|
||||
|
||||
- **Transcription Services:** Convert spoken Arabic content, such as audio recordings, podcasts, or videos, into written text for indexing, search, or translation purposes.
|
||||
|
||||
- **Voice Assistants:** Enhance voice-activated systems and virtual assistants with accurate Arabic speech recognition capabilities.
|
||||
|
||||
- **Language Processing Applications:** Integrate the model into applications involving Arabic language processing, such as sentiment analysis, keyword extraction, and more.
|
||||
|
||||
- **Multilingual ASR:** Combine Whisper-small-ar with other multilingual ASR models for applications requiring recognition of multiple languages.
|
||||
|
||||
## Usage
|
||||
```python
|
||||
# Use a pipeline as a high-level helper
|
||||
from transformers import pipeline
|
||||
|
||||
pipe = pipeline("automatic-speech-recognition", model="ayoubkirouane/whisper-small-ar")
|
||||
|
||||
def transcribe(audio):
|
||||
text = pipe(audio)["text"]
|
||||
return text
|
||||
```
|
||||
1609
added_tokens.json
Normal file
1609
added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
52
config.json
Normal file
52
config.json
Normal file
@@ -0,0 +1,52 @@
|
||||
{
|
||||
"_name_or_path": "openai/whisper-small",
|
||||
"activation_dropout": 0.0,
|
||||
"activation_function": "gelu",
|
||||
"apply_spec_augment": false,
|
||||
"architectures": [
|
||||
"WhisperForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"begin_suppress_tokens": [
|
||||
220,
|
||||
50257
|
||||
],
|
||||
"bos_token_id": 50257,
|
||||
"classifier_proj_size": 256,
|
||||
"d_model": 768,
|
||||
"decoder_attention_heads": 12,
|
||||
"decoder_ffn_dim": 3072,
|
||||
"decoder_layerdrop": 0.0,
|
||||
"decoder_layers": 12,
|
||||
"decoder_start_token_id": 50258,
|
||||
"dropout": 0.0,
|
||||
"encoder_attention_heads": 12,
|
||||
"encoder_ffn_dim": 3072,
|
||||
"encoder_layerdrop": 0.0,
|
||||
"encoder_layers": 12,
|
||||
"eos_token_id": 50257,
|
||||
"forced_decoder_ids": null,
|
||||
"init_std": 0.02,
|
||||
"is_encoder_decoder": true,
|
||||
"mask_feature_length": 10,
|
||||
"mask_feature_min_masks": 0,
|
||||
"mask_feature_prob": 0.0,
|
||||
"mask_time_length": 10,
|
||||
"mask_time_min_masks": 2,
|
||||
"mask_time_prob": 0.05,
|
||||
"max_length": 448,
|
||||
"max_source_positions": 1500,
|
||||
"max_target_positions": 448,
|
||||
"median_filter_width": 7,
|
||||
"model_type": "whisper",
|
||||
"num_hidden_layers": 12,
|
||||
"num_mel_bins": 80,
|
||||
"pad_token_id": 50257,
|
||||
"scale_embedding": false,
|
||||
"suppress_tokens": [],
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.33.2",
|
||||
"use_cache": true,
|
||||
"use_weighted_layer_sum": false,
|
||||
"vocab_size": 51865
|
||||
}
|
||||
263
generation_config.json
Normal file
263
generation_config.json
Normal file
@@ -0,0 +1,263 @@
|
||||
{
|
||||
"alignment_heads": [
|
||||
[
|
||||
5,
|
||||
3
|
||||
],
|
||||
[
|
||||
5,
|
||||
9
|
||||
],
|
||||
[
|
||||
8,
|
||||
0
|
||||
],
|
||||
[
|
||||
8,
|
||||
4
|
||||
],
|
||||
[
|
||||
8,
|
||||
7
|
||||
],
|
||||
[
|
||||
8,
|
||||
8
|
||||
],
|
||||
[
|
||||
9,
|
||||
0
|
||||
],
|
||||
[
|
||||
9,
|
||||
7
|
||||
],
|
||||
[
|
||||
9,
|
||||
9
|
||||
],
|
||||
[
|
||||
10,
|
||||
5
|
||||
]
|
||||
],
|
||||
"begin_suppress_tokens": [
|
||||
220,
|
||||
50257
|
||||
],
|
||||
"bos_token_id": 50257,
|
||||
"decoder_start_token_id": 50258,
|
||||
"eos_token_id": 50257,
|
||||
"forced_decoder_ids": [
|
||||
[
|
||||
1,
|
||||
null
|
||||
],
|
||||
[
|
||||
2,
|
||||
50359
|
||||
]
|
||||
],
|
||||
"is_multilingual": true,
|
||||
"lang_to_id": {
|
||||
"<|af|>": 50327,
|
||||
"<|am|>": 50334,
|
||||
"<|ar|>": 50272,
|
||||
"<|as|>": 50350,
|
||||
"<|az|>": 50304,
|
||||
"<|ba|>": 50355,
|
||||
"<|be|>": 50330,
|
||||
"<|bg|>": 50292,
|
||||
"<|bn|>": 50302,
|
||||
"<|bo|>": 50347,
|
||||
"<|br|>": 50309,
|
||||
"<|bs|>": 50315,
|
||||
"<|ca|>": 50270,
|
||||
"<|cs|>": 50283,
|
||||
"<|cy|>": 50297,
|
||||
"<|da|>": 50285,
|
||||
"<|de|>": 50261,
|
||||
"<|el|>": 50281,
|
||||
"<|en|>": 50259,
|
||||
"<|es|>": 50262,
|
||||
"<|et|>": 50307,
|
||||
"<|eu|>": 50310,
|
||||
"<|fa|>": 50300,
|
||||
"<|fi|>": 50277,
|
||||
"<|fo|>": 50338,
|
||||
"<|fr|>": 50265,
|
||||
"<|gl|>": 50319,
|
||||
"<|gu|>": 50333,
|
||||
"<|haw|>": 50352,
|
||||
"<|ha|>": 50354,
|
||||
"<|he|>": 50279,
|
||||
"<|hi|>": 50276,
|
||||
"<|hr|>": 50291,
|
||||
"<|ht|>": 50339,
|
||||
"<|hu|>": 50286,
|
||||
"<|hy|>": 50312,
|
||||
"<|id|>": 50275,
|
||||
"<|is|>": 50311,
|
||||
"<|it|>": 50274,
|
||||
"<|ja|>": 50266,
|
||||
"<|jw|>": 50356,
|
||||
"<|ka|>": 50329,
|
||||
"<|kk|>": 50316,
|
||||
"<|km|>": 50323,
|
||||
"<|kn|>": 50306,
|
||||
"<|ko|>": 50264,
|
||||
"<|la|>": 50294,
|
||||
"<|lb|>": 50345,
|
||||
"<|ln|>": 50353,
|
||||
"<|lo|>": 50336,
|
||||
"<|lt|>": 50293,
|
||||
"<|lv|>": 50301,
|
||||
"<|mg|>": 50349,
|
||||
"<|mi|>": 50295,
|
||||
"<|mk|>": 50308,
|
||||
"<|ml|>": 50296,
|
||||
"<|mn|>": 50314,
|
||||
"<|mr|>": 50320,
|
||||
"<|ms|>": 50282,
|
||||
"<|mt|>": 50343,
|
||||
"<|my|>": 50346,
|
||||
"<|ne|>": 50313,
|
||||
"<|nl|>": 50271,
|
||||
"<|nn|>": 50342,
|
||||
"<|no|>": 50288,
|
||||
"<|oc|>": 50328,
|
||||
"<|pa|>": 50321,
|
||||
"<|pl|>": 50269,
|
||||
"<|ps|>": 50340,
|
||||
"<|pt|>": 50267,
|
||||
"<|ro|>": 50284,
|
||||
"<|ru|>": 50263,
|
||||
"<|sa|>": 50344,
|
||||
"<|sd|>": 50332,
|
||||
"<|si|>": 50322,
|
||||
"<|sk|>": 50298,
|
||||
"<|sl|>": 50305,
|
||||
"<|sn|>": 50324,
|
||||
"<|so|>": 50326,
|
||||
"<|sq|>": 50317,
|
||||
"<|sr|>": 50303,
|
||||
"<|su|>": 50357,
|
||||
"<|sv|>": 50273,
|
||||
"<|sw|>": 50318,
|
||||
"<|ta|>": 50287,
|
||||
"<|te|>": 50299,
|
||||
"<|tg|>": 50331,
|
||||
"<|th|>": 50289,
|
||||
"<|tk|>": 50341,
|
||||
"<|tl|>": 50348,
|
||||
"<|tr|>": 50268,
|
||||
"<|tt|>": 50351,
|
||||
"<|uk|>": 50280,
|
||||
"<|ur|>": 50290,
|
||||
"<|uz|>": 50337,
|
||||
"<|vi|>": 50278,
|
||||
"<|yi|>": 50335,
|
||||
"<|yo|>": 50325,
|
||||
"<|zh|>": 50260
|
||||
},
|
||||
"max_initial_timestamp_index": 1,
|
||||
"max_length": 448,
|
||||
"no_timestamps_token_id": 50363,
|
||||
"pad_token_id": 50257,
|
||||
"return_timestamps": false,
|
||||
"suppress_tokens": [
|
||||
1,
|
||||
2,
|
||||
7,
|
||||
8,
|
||||
9,
|
||||
10,
|
||||
14,
|
||||
25,
|
||||
26,
|
||||
27,
|
||||
28,
|
||||
29,
|
||||
31,
|
||||
58,
|
||||
59,
|
||||
60,
|
||||
61,
|
||||
62,
|
||||
63,
|
||||
90,
|
||||
91,
|
||||
92,
|
||||
93,
|
||||
359,
|
||||
503,
|
||||
522,
|
||||
542,
|
||||
873,
|
||||
893,
|
||||
902,
|
||||
918,
|
||||
922,
|
||||
931,
|
||||
1350,
|
||||
1853,
|
||||
1982,
|
||||
2460,
|
||||
2627,
|
||||
3246,
|
||||
3253,
|
||||
3268,
|
||||
3536,
|
||||
3846,
|
||||
3961,
|
||||
4183,
|
||||
4667,
|
||||
6585,
|
||||
6647,
|
||||
7273,
|
||||
9061,
|
||||
9383,
|
||||
10428,
|
||||
10929,
|
||||
11938,
|
||||
12033,
|
||||
12331,
|
||||
12562,
|
||||
13793,
|
||||
14157,
|
||||
14635,
|
||||
15265,
|
||||
15618,
|
||||
16553,
|
||||
16604,
|
||||
18362,
|
||||
18956,
|
||||
20075,
|
||||
21675,
|
||||
22520,
|
||||
26130,
|
||||
26161,
|
||||
26435,
|
||||
28279,
|
||||
29464,
|
||||
31650,
|
||||
32302,
|
||||
32470,
|
||||
36865,
|
||||
42863,
|
||||
47425,
|
||||
49870,
|
||||
50254,
|
||||
50258,
|
||||
50358,
|
||||
50359,
|
||||
50360,
|
||||
50361,
|
||||
50362
|
||||
],
|
||||
"task_to_id": {
|
||||
"transcribe": 50359,
|
||||
"translate": 50358
|
||||
},
|
||||
"transformers_version": "4.33.2"
|
||||
}
|
||||
50000
merges.txt
Normal file
50000
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
1742
normalizer.json
Normal file
1742
normalizer.json
Normal file
File diff suppressed because it is too large
Load Diff
14
preprocessor_config.json
Normal file
14
preprocessor_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"chunk_length": 30,
|
||||
"feature_extractor_type": "WhisperFeatureExtractor",
|
||||
"feature_size": 80,
|
||||
"hop_length": 160,
|
||||
"n_fft": 400,
|
||||
"n_samples": 480000,
|
||||
"nb_max_frames": 3000,
|
||||
"padding_side": "right",
|
||||
"padding_value": 0.0,
|
||||
"processor_class": "WhisperProcessor",
|
||||
"return_attention_mask": false,
|
||||
"sampling_rate": 16000
|
||||
}
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f58e00c126163313f4e882dfad4b8093583dd83befa8c8c1cc23c576eb606af4
|
||||
size 967102729
|
||||
133
special_tokens_map.json
Normal file
133
special_tokens_map.json
Normal file
@@ -0,0 +1,133 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|startoftranscript|>",
|
||||
"<|en|>",
|
||||
"<|zh|>",
|
||||
"<|de|>",
|
||||
"<|es|>",
|
||||
"<|ru|>",
|
||||
"<|ko|>",
|
||||
"<|fr|>",
|
||||
"<|ja|>",
|
||||
"<|pt|>",
|
||||
"<|tr|>",
|
||||
"<|pl|>",
|
||||
"<|ca|>",
|
||||
"<|nl|>",
|
||||
"<|ar|>",
|
||||
"<|sv|>",
|
||||
"<|it|>",
|
||||
"<|id|>",
|
||||
"<|hi|>",
|
||||
"<|fi|>",
|
||||
"<|vi|>",
|
||||
"<|he|>",
|
||||
"<|uk|>",
|
||||
"<|el|>",
|
||||
"<|ms|>",
|
||||
"<|cs|>",
|
||||
"<|ro|>",
|
||||
"<|da|>",
|
||||
"<|hu|>",
|
||||
"<|ta|>",
|
||||
"<|no|>",
|
||||
"<|th|>",
|
||||
"<|ur|>",
|
||||
"<|hr|>",
|
||||
"<|bg|>",
|
||||
"<|lt|>",
|
||||
"<|la|>",
|
||||
"<|mi|>",
|
||||
"<|ml|>",
|
||||
"<|cy|>",
|
||||
"<|sk|>",
|
||||
"<|te|>",
|
||||
"<|fa|>",
|
||||
"<|lv|>",
|
||||
"<|bn|>",
|
||||
"<|sr|>",
|
||||
"<|az|>",
|
||||
"<|sl|>",
|
||||
"<|kn|>",
|
||||
"<|et|>",
|
||||
"<|mk|>",
|
||||
"<|br|>",
|
||||
"<|eu|>",
|
||||
"<|is|>",
|
||||
"<|hy|>",
|
||||
"<|ne|>",
|
||||
"<|mn|>",
|
||||
"<|bs|>",
|
||||
"<|kk|>",
|
||||
"<|sq|>",
|
||||
"<|sw|>",
|
||||
"<|gl|>",
|
||||
"<|mr|>",
|
||||
"<|pa|>",
|
||||
"<|si|>",
|
||||
"<|km|>",
|
||||
"<|sn|>",
|
||||
"<|yo|>",
|
||||
"<|so|>",
|
||||
"<|af|>",
|
||||
"<|oc|>",
|
||||
"<|ka|>",
|
||||
"<|be|>",
|
||||
"<|tg|>",
|
||||
"<|sd|>",
|
||||
"<|gu|>",
|
||||
"<|am|>",
|
||||
"<|yi|>",
|
||||
"<|lo|>",
|
||||
"<|uz|>",
|
||||
"<|fo|>",
|
||||
"<|ht|>",
|
||||
"<|ps|>",
|
||||
"<|tk|>",
|
||||
"<|nn|>",
|
||||
"<|mt|>",
|
||||
"<|sa|>",
|
||||
"<|lb|>",
|
||||
"<|my|>",
|
||||
"<|bo|>",
|
||||
"<|tl|>",
|
||||
"<|mg|>",
|
||||
"<|as|>",
|
||||
"<|tt|>",
|
||||
"<|haw|>",
|
||||
"<|ln|>",
|
||||
"<|ha|>",
|
||||
"<|ba|>",
|
||||
"<|jw|>",
|
||||
"<|su|>",
|
||||
"<|translate|>",
|
||||
"<|transcribe|>",
|
||||
"<|startoflm|>",
|
||||
"<|startofprev|>",
|
||||
"<|nocaptions|>",
|
||||
"<|notimestamps|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"errors": "replace",
|
||||
"model_max_length": 1024,
|
||||
"pad_token": null,
|
||||
"processor_class": "WhisperProcessor",
|
||||
"return_attention_mask": false,
|
||||
"tokenizer_class": "WhisperTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:af37a702d181ade78a944b27863ccb069c2895843dde15db36d5f0e9938cce5a
|
||||
size 4155
|
||||
50260
vocab.json
Normal file
50260
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user