Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
mozilla-foundation/common_voice_7_0
Generated from Trainer
Instructions to use jcmc/wav2vec2-xls-r-1b-ir with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jcmc/wav2vec2-xls-r-1b-ir with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jcmc/wav2vec2-xls-r-1b-ir")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("jcmc/wav2vec2-xls-r-1b-ir") model = AutoModelForCTC.from_pretrained("jcmc/wav2vec2-xls-r-1b-ir", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 500
Browse files- .ipynb_checkpoints/run-checkpoint.sh +2 -2
- pytorch_model.bin +1 -1
- run.sh +2 -2
- special_tokens_map.json +1 -1
- training_args.bin +1 -1
.ipynb_checkpoints/run-checkpoint.sh
CHANGED
|
@@ -5,8 +5,8 @@ python run_speech_recognition_ctc_bnb.py \
|
|
| 5 |
--output_dir="./" \
|
| 6 |
--overwrite_output_dir \
|
| 7 |
--num_train_epochs="100" \
|
| 8 |
-
--per_device_train_batch_size="
|
| 9 |
-
--per_device_eval_batch_size="
|
| 10 |
--gradient_accumulation_steps="4" \
|
| 11 |
--learning_rate="5e-5" \
|
| 12 |
--warmup_steps="500" \
|
|
|
|
| 5 |
--output_dir="./" \
|
| 6 |
--overwrite_output_dir \
|
| 7 |
--num_train_epochs="100" \
|
| 8 |
+
--per_device_train_batch_size="8" \
|
| 9 |
+
--per_device_eval_batch_size="8" \
|
| 10 |
--gradient_accumulation_steps="4" \
|
| 11 |
--learning_rate="5e-5" \
|
| 12 |
--warmup_steps="500" \
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850486961
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58cae0744a6cf60629cb098bc9b07d88bd0a018bd4da473af5b9664dd56d968c
|
| 3 |
size 3850486961
|
run.sh
CHANGED
|
@@ -5,8 +5,8 @@ python run_speech_recognition_ctc_bnb.py \
|
|
| 5 |
--output_dir="./" \
|
| 6 |
--overwrite_output_dir \
|
| 7 |
--num_train_epochs="100" \
|
| 8 |
-
--per_device_train_batch_size="
|
| 9 |
-
--per_device_eval_batch_size="
|
| 10 |
--gradient_accumulation_steps="4" \
|
| 11 |
--learning_rate="5e-5" \
|
| 12 |
--warmup_steps="500" \
|
|
|
|
| 5 |
--output_dir="./" \
|
| 6 |
--overwrite_output_dir \
|
| 7 |
--num_train_epochs="100" \
|
| 8 |
+
--per_device_train_batch_size="8" \
|
| 9 |
+
--per_device_eval_batch_size="8" \
|
| 10 |
--gradient_accumulation_steps="4" \
|
| 11 |
--learning_rate="5e-5" \
|
| 12 |
--warmup_steps="500" \
|
special_tokens_map.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2991
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e198f77fb43c23120b701ca29ceab42568fa65b2ec2dbb80c249025ed863307f
|
| 3 |
size 2991
|