merge with whisper-small-yue-full-1

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+base_model: safecantonese/whisper-small-yue-full
+model-index:
+- name: whisper-small-yue-full-1
+  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. -->
+
+# whisper-small-yue-full-1
+
+This model is a fine-tuned version of [safecantonese/whisper-small-yue-full](https://huggingface.co/safecantonese/whisper-small-yue-full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0362
+- Cer: 6.1457
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 2000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0147        | 0.88  | 1000 | 0.0406          | 6.2936 |
+| 0.0083        | 1.76  | 2000 | 0.0362          | 6.1457 |
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "safecantonese/whisper-small-yue-full",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

generation_config.json

@@ -0,0 +1,27 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50260
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "suppress_tokens": [],
+  "transformers_version": "4.38.0.dev0"
+}

ggml/ggml-model-q5_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9419a6e4af59c446f68cb23eb6fa7e878b4cfb9989a3c6e621c3e954b0ac66c4
+size 175209680

ggml/ggml-model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f815dd20ba7aafc97a6e79fc186f436f3689c03dc7e4e3501ea8202f9cdf611
+size 487601984

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:878a2de84c53ce31d490c5e7cbed78bfb421f90386b95c0a7f2eecd0482605cd
+oid sha256:e84c1a3876cbe8b0636e64210712ed6410f8e39ca432efbc072133aa49decb0b
 size 966995080

runs/Feb07_15-10-58_84b21c4f8d12/events.out.tfevents.1707318661.84b21c4f8d12.2395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36d30e927900ccae1039014601f800f20981daba7bdbccb0b00236eb50c9353
+size 18944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4086b95014e5ddf744d923d41823bdb962b8658eb0f182fbec277dc30c0786cc
+oid sha256:a42c93de41395feac499e9dccd42c33af66e7360152fbe2e0924e06dd733085f
 size 4920