Model save

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/speecht5_asr
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: speecht5-tunis_finalll
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# speecht5-tunis_finalll
+
+This model is a fine-tuned version of [microsoft/speecht5_asr](https://huggingface.co/microsoft/speecht5_asr) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1951
+- Wer Ortho: 63.3333
+- Wer: 62.4672
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer      |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:--------:|
+| 1.7381        | 0.3731 | 100  | 1.4437          | 371.3889  | 213.9108 |
+| 0.8437        | 0.7463 | 200  | 0.5686          | 80.5556   | 81.6273  |
+| 0.4461        | 1.1194 | 300  | 0.3668          | 76.1111   | 77.4278  |
+| 0.3753        | 1.4925 | 400  | 0.2760          | 72.7778   | 74.0157  |
+| 0.3416        | 1.8657 | 500  | 0.2392          | 80.8333   | 84.7769  |
+| 0.2656        | 2.2388 | 600  | 0.2138          | 67.7778   | 67.9790  |
+| 0.2706        | 2.6119 | 700  | 0.2085          | 74.7222   | 77.1654  |
+| 0.2509        | 2.9851 | 800  | 0.1995          | 63.0556   | 62.2047  |
+| 0.2314        | 3.3582 | 900  | 0.1949          | 62.5      | 61.6798  |
+| 0.2806        | 3.7313 | 1000 | 0.1951          | 63.3333   | 62.4672  |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

final_model/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}

final_model/config.json

@@ -0,0 +1,92 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForSpeechToText"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "forced_decoder_ids": null,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "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_speech_positions": 4000,
+  "max_text_positions": 450,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

final_model/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 450,
+  "pad_token_id": 1,
+  "suppress_tokens": [],
+  "transformers_version": "4.52.4",
+  "use_cache": false
+}

final_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc61cb1446fcbb6002384682ffdd95b1f127033e00738521480a2388356e233
+size 604711248

final_model/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}

final_model/special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

final_model/spm_char.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473

final_model/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 450,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}

final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1870232b40870feeeb9e828e86f936d1b7f61afd2c72c99e07956df5e914e39
+size 5432

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 450,
+  "pad_token_id": 1,
+  "suppress_tokens": [],
+  "transformers_version": "4.52.4",
+  "use_cache": false
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35bb2d4a90141447e7b9b101c8f18fcf7616e9c18d825de7f8a4108f6dc993bd
+oid sha256:3dc61cb1446fcbb6002384682ffdd95b1f127033e00738521480a2388356e233
 size 604711248