# Load fine tuned model in tensorflow
**URL:**
**Author:**  [@ahmedlone123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahmedlone123)%5C
**Post date:** [August 3, 2021, 9:37am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F1 "2021-08-03T09:37:30Z")
I fine-tuned a pre-trained model(wav2vec) in hugging face using the transformers library and converted it from PyTorch to Tensorflow. I want to load this fine-tuned model in Tensorlfow but I can’t seem to find any tutorials showcasing how to. Any help would be appreciated.
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [August 3, 2021, 10:59am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F2 "2021-08-03T10:59:49Z")
```auto
from transformers import TFWav2Vec2ForXxx
TFWav2Vec2ForXxx.from_pretrained(model_name_or_path)
```
where `model_name_or_path` is the folder where you stored that model, or the name of the repo you pushed it to on the Hugging Face Hub.
---
**Author:**  [@ahmedlone123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahmedlone123)%5C
**Post date:** [August 3, 2021, 1:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F3 "2021-08-03T13:12:46Z")
How would i load this model in tensorflow , wouldn’t this be loading it using huggingface ?
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [August 3, 2021, 4:06pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F4 "2021-08-03T16:06:25Z")
The TensorFlow library does not offer an implementation of the Wav2Vec2 model, so I’m not sure how you would like to be loading it without using Transformers.
---
**Author:**  [@ahmedlone123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahmedlone123)%5C
**Post date:** [August 3, 2021, 4:17pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F5 "2021-08-03T16:17:04Z")
[https://tfhub.dev/vasudevgupta7/wav2vec2/1](https://tfhub.dev/vasudevgupta7/wav2vec2/1)
well there is this
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [August 3, 2021, 4:19pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F6 "2021-08-03T16:19:39Z")
This is one particular model, not the architecture. Since the person that added it to the TF Hub is a core contributor to Transformers, it’s probably the same code as in the library behind it.
---
**Author:**  [@ahmedlone123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahmedlone123)%5C
**Post date:** [August 3, 2021, 4:23pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F7 "2021-08-03T16:23:44Z")
okay thank you i am going to try to retrain the model in pure tenserflow
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [August 3, 2021, 4:35pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F8 "2021-08-03T16:35:59Z")
I’m not sure you need to, you can save the model loaded as above in any pure TF format you want. As you would when retraining the model in pure TensorFlow.
---
**Author:**  [@ahmedlone123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahmedlone123)%5C
**Post date:** [August 3, 2021, 4:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F9 "2021-08-03T16:45:59Z")
Well my main goal is to be able to load the wav2vec model inside tensorflow and after training a pytroch model inside hugging face and converting it to tensorflow I get a h5 file and a seperate config file .
when I try to load it like this it gives me this error but when I try running this notebook:
[https://colab.research.google.com/github/vasudevgupta7/gsoc-wav2vec2/blob/main/notebooks/wav2vec2\_saved\_model\_finetuning.ipynb](https://colab.research.google.com/github/vasudevgupta7/gsoc-wav2vec2/blob/main/notebooks/wav2vec2_saved_model_finetuning.ipynb)
which is the wav2vec model the guy upload to tensorflow this part works :
soo Idk what’s wrong with this .
Thank you for being patient with me
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [August 3, 2021, 4:56pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F10 "2021-08-03T16:56:03Z")
As I said, first load it inside a `TFWav2Vec2ForXxx` model (I’m not sure exactly which model you used, replaced the Xxx to the proper name). You can do this with
```auto
TFWav2Vec2ForXxx.from_pretrained(path_to_pytorch_model, from_pt=True)
```
This model will be a Keras model. You can save it using Keras, so should be able to then load it with Keras.
---
**Author:**  [@ahmedlone123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahmedlone123)%5C
**Post date:** [August 3, 2021, 4:56pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F11 "2021-08-03T16:56:48Z")
okay thank you i will try this i am sorry for wasting ur time
---
**Author:**  [@ahmedlone123](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahmedlone123)%5C
**Post date:** [August 3, 2021, 5:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fload-fine-tuned-model-in-tensorflow%2F8932%2F12 "2021-08-03T17:15:32Z")
I tried it :
I tried this way too :
