Upload WhisperForConditionalGeneration

README.md

@@ -1,79 +1,3 @@
----
-library_name: transformers
-license: mit
-datasets:
-- NhutP/VSV-1100
-- mozilla-foundation/common_voice_14_0
-- AILAB-VNUHCM/vivos
-language:
-- vi
-metrics:
-- wer
-base_model:
-- openai/whisper-medium
----
-## Introduction
-- We release a new model for Vietnamese speech regconition task.
-- We fine-tuned [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on our new dataset [VSV-1100](https://huggingface.co/datasets/NhutP/VSV-1100).
-
-## Training data
-
-| [VSV-1100](https://huggingface.co/datasets/NhutP/VSV-1100) | T2S* | [CMV14-vi](https://huggingface.co/datasets/mozilla-foundation/common_voice_14_0) |[VIVOS](https://huggingface.co/datasets/AILAB-VNUHCM/vivos)| [VLSP2021](https://vlsp.org.vn/index.php/resources) | Total|
-|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
-|   1100 hours  |   11  hours |   3.04 hours  |    13.94  hours| 180 hours | 1308 hours |
-
-\* We use a text-to-speech model to generate sentences containing words that do not appear in our dataset.
-
-## WER result
-| [CMV14-vi](https://huggingface.co/datasets/mozilla-foundation/common_voice_14_0) | [VIVOS](https://huggingface.co/datasets/AILAB-VNUHCM/vivos) | [VLSP2020-T1](https://vlsp.org.vn/index.php/resources) | [VLSP2020-T2](https://vlsp.org.vn/index.php/resources) | [VLSP2021-T1](https://vlsp.org.vn/index.php/resources) | [VLSP2021-T2](https://vlsp.org.vn/index.php/resources) |[Bud500](https://huggingface.co/datasets/linhtran92/viet_bud500) |
-|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
-|8.1|4.69|13.22|28.76| 11.78 | 8.28 | 5.38 |
-
-
-
-## Usage
-### Inference
-```python
-from transformers import WhisperProcessor, WhisperForConditionalGeneration
-import librosa
-# load model and processor
-processor = WhisperProcessor.from_pretrained("NhutP/ViWhisper-medium")
-model = WhisperForConditionalGeneration.from_pretrained("NhutP/ViWhisper-medium")
-model.config.forced_decoder_ids = None
-
-# load a sample
-array, sampling_rate = librosa.load('path_to_audio', sr = 16000) # Load some audio sample
-input_features = processor(array, sampling_rate=sampling_rate, return_tensors="pt").input_features 
-# generate token ids
-predicted_ids = model.generate(input_features)
-# decode token ids to text
-transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
-```
-### Use with pipeline
-```python
-from transformers import pipeline
-pipe = pipeline(
-    "automatic-speech-recognition",
-    model="NhutP/ViWhisper-medium",
-    max_new_tokens=128,
-    chunk_length_s=30,
-    return_timestamps=False,
-    device= '...' # 'cpu' or 'cuda'
-) 
-output = pipe(path_to_audio_samplingrate_16000)['text']
-```
-
-## Citation
-
-```
-@misc{VSV-1100,
-    author = {Pham Quang Nhut and Duong Pham Hoang Anh and Nguyen Vinh Tiep},
-    title = {VSV-1100: Vietnamese social voice dataset},
-    url = {https://github.com/NhutP/VSV-1100},
-    year = {2024}
-}
-```
-
-Also, please give us a star on github: https://github.com/NhutP/ViWhisper if you find our project useful
-
-Contact me at: [email protected] (Pham Quang Nhut)
+---
+license: mit
+---

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "C:\\Users\\quang\\Desktop\\eval_medium\\checkpoint-95368",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "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": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 24,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,250 @@
+{
+  "alignment_heads": [
+    [
+      13,
+      15
+    ],
+    [
+      15,
+      4
+    ],
+    [
+      15,
+      15
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      20,
+      0
+    ],
+    [
+      23,
+      4
+    ]
+  ],
+  "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
+  },
+  "language": "vi",
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "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": "4.38.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84459b728f973ff4585d12242ace01ececfb68235964ad6a0f122e709c6aeab5
+size 3055544304