update model card README.md

.ipynb_checkpoints/config-checkpoint.json

@@ -1,107 +0,0 @@
-{
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
-  "activation_dropout": 0.1,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
-  "architectures": [
-    "Wav2Vec2ForCTC"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "codevector_dim": 768,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
-  "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
-  ],
-  "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": false,
-  "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.0,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "mask_feature_length": 64,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.25,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.75,
-  "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
-  "num_attention_heads": 16,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
-  "num_negatives": 100,
-  "output_hidden_size": 1024,
-  "pad_token_id": 40,
-  "proj_codevector_dim": 768,
-  "tdnn_dilation": [
-    1,
-    2,
-    3,
-    1,
-    1
-  ],
-  "tdnn_dim": [
-    512,
-    512,
-    512,
-    512,
-    1500
-  ],
-  "tdnn_kernel": [
-    5,
-    3,
-    3,
-    1,
-    1
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.17.0.dev0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 41,
-  "xvector_output_dim": 512
-}

.ipynb_checkpoints/vocab-checkpoint.json

@@ -1 +0,0 @@
-{"'": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "à": 28, "â": 29, "ç": 30, "è": 31, "é": 32, "ê": 33, "î": 34, "ï": 35, "ô": 36, "ù": 37, "û": 38, "|": 0, "[UNK]": 39, "[PAD]": 40}

README.md

@@ -1,10 +1,6 @@
 ---
-language:
-- fr
 license: apache-2.0
 tags:
-- automatic-speech-recognition
-- mozilla-foundation/common_voice_7_0
 - generated_from_trainer
 model-index:
 - name: ''
@@ -16,10 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - FR dataset.
-It achieves the following results on the evaluation set:
-- Loss: 16.9132
-- Wer: 2.3630
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
 
 ## Model description
 
@@ -47,7 +40,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2000
-- num_epochs: 0.2
+- num_epochs: 0.4
 - mixed_precision_training: Native AMP
 
 ### Training results

all_results.json

@@ -1,14 +0,0 @@
-{
-    "epoch": 0.19,
-    "eval_loss": 16.913198471069336,
-    "eval_runtime": 8.6705,
-    "eval_samples": 200,
-    "eval_samples_per_second": 23.067,
-    "eval_steps_per_second": 2.883,
-    "eval_wer": 2.3629935179728934,
-    "train_loss": 12.496875762939453,
-    "train_runtime": 12.893,
-    "train_samples": 1000,
-    "train_samples_per_second": 15.512,
-    "train_steps_per_second": 0.233
-}

config.json

@@ -1,107 +0,0 @@
-{
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
-  "activation_dropout": 0.1,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
-  "architectures": [
-    "Wav2Vec2ForCTC"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "codevector_dim": 768,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
-  "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
-  ],
-  "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": false,
-  "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.0,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "mask_feature_length": 64,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.25,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.75,
-  "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
-  "num_attention_heads": 16,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
-  "num_negatives": 100,
-  "output_hidden_size": 1024,
-  "pad_token_id": 40,
-  "proj_codevector_dim": 768,
-  "tdnn_dilation": [
-    1,
-    2,
-    3,
-    1,
-    1
-  ],
-  "tdnn_dim": [
-    512,
-    512,
-    512,
-    512,
-    1500
-  ],
-  "tdnn_kernel": [
-    5,
-    3,
-    3,
-    1,
-    1
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.17.0.dev0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 41,
-  "xvector_output_dim": 512
-}

eval_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 0.19,
-    "eval_loss": 16.913198471069336,
-    "eval_runtime": 8.6705,
-    "eval_samples": 200,
-    "eval_samples_per_second": 23.067,
-    "eval_steps_per_second": 2.883,
-    "eval_wer": 2.3629935179728934
-}

preprocessor_config.json

@@ -1,9 +0,0 @@
-{
-  "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
-  "feature_size": 1,
-  "padding_side": "right",
-  "padding_value": 0,
-  "return_attention_mask": true,
-  "sampling_rate": 16000
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d1d7bd7ffd2ed6a01faf9f143c79eb1c4a1e163dd1a62f92c26af28850511bcd
-size 1262091761

special_tokens_map.json

@@ -1 +0,0 @@
-{"unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -1 +0,0 @@
-{"unk_token": "[UNK]", "bos_token": null, "eos_token": null, "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 0.19,
-    "train_loss": 12.496875762939453,
-    "train_runtime": 12.893,
-    "train_samples": 1000,
-    "train_samples_per_second": 15.512,
-    "train_steps_per_second": 0.233
-}

trainer_state.json

@@ -1,25 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.192,
-  "global_step": 3,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.19,
-      "step": 3,
-      "total_flos": 2.67196543170048e+16,
-      "train_loss": 12.496875762939453,
-      "train_runtime": 12.893,
-      "train_samples_per_second": 15.512,
-      "train_steps_per_second": 0.233
-    }
-  ],
-  "max_steps": 3,
-  "num_train_epochs": 1,
-  "total_flos": 2.67196543170048e+16,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a4f6b5e530f353910710ef95150e349ddf6f70545b8095619803d7da46090983
-size 2991

vocab.json

@@ -1 +0,0 @@
-{"'": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "à": 28, "â": 29, "ç": 30, "è": 31, "é": 32, "ê": 33, "î": 34, "ï": 35, "ô": 36, "ù": 37, "û": 38, "|": 0, "[UNK]": 39, "[PAD]": 40}

wandb/run-20220130_230018-ktkg6ghu/files/output.log

@@ -15,3 +15,11 @@ Configuration saved in ./preprocessor_config.json
 Saving model checkpoint to ./
 Configuration saved in ./config.json
 Model weights saved in ./pytorch_model.bin
+Configuration saved in ./preprocessor_config.json
+Upload file pytorch_model.bin:   1%|▋                                                                                                | 8.55M/1.18G [00:01<02:22, 8.82MB/s]
+Upload file training_args.bin: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 2.92k/2.92k [00:00<?, ?B/s]
+01/30/2022 23:02:55 - WARNING - huggingface_hub.repository - To https://huggingface.co/Plim/xls-r-300m-fr
+   1fb68dc..ab9abf3  main -> main0%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 2.92k/2.92k [00:00<?, ?B/s]
+Upload file pytorch_model.bin: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 1.18G/1.18G [00:50<00:00, 25.0MB/s]
+Upload file training_args.bin: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 2.92k/2.92k [00:50<?, ?B/s]
+Dropping the following result as it does not have all the necessary fields:██████████████████████████████████████████████████████████████████| 2.92k/2.92k [00:50<?, ?B/s]

wandb/run-20220130_230018-ktkg6ghu/logs/debug-internal.log

@@ -68,3 +68,16 @@
 2022-01-30 23:01:48,941 DEBUG   SenderThread:28776 [sender.py:send():234] send: stats
 2022-01-30 23:01:51,982 DEBUG   HandlerThread:28776 [handler.py:handle_request():130] handle_request: stop_status
 2022-01-30 23:01:51,982 DEBUG   SenderThread:28776 [sender.py:send_request():248] send_request: stop_status
+2022-01-30 23:02:07,146 DEBUG   HandlerThread:28776 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-30 23:02:07,146 DEBUG   SenderThread:28776 [sender.py:send_request():248] send_request: stop_status
+2022-01-30 23:02:07,242 INFO    Thread-8  :28776 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220130_230018-ktkg6ghu/files/output.log
+2022-01-30 23:02:19,172 DEBUG   SenderThread:28776 [sender.py:send():234] send: stats
+2022-01-30 23:02:22,319 DEBUG   HandlerThread:28776 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-30 23:02:22,319 DEBUG   SenderThread:28776 [sender.py:send_request():248] send_request: stop_status
+2022-01-30 23:02:37,476 DEBUG   HandlerThread:28776 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-30 23:02:37,476 DEBUG   SenderThread:28776 [sender.py:send_request():248] send_request: stop_status
+2022-01-30 23:02:49,382 DEBUG   SenderThread:28776 [sender.py:send():234] send: stats
+2022-01-30 23:02:52,639 DEBUG   HandlerThread:28776 [handler.py:handle_request():130] handle_request: stop_status
+2022-01-30 23:02:52,640 DEBUG   SenderThread:28776 [sender.py:send_request():248] send_request: stop_status
+2022-01-30 23:02:57,275 INFO    Thread-8  :28776 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220130_230018-ktkg6ghu/files/output.log
+2022-01-30 23:02:59,276 INFO    Thread-8  :28776 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220130_230018-ktkg6ghu/files/output.log