Audio-Text-to-Text
Safetensors
English
llama
sound language model
jan-hq commited on
Commit
9deb2ea
1 Parent(s): 46592a2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +145 -137
README.md CHANGED
@@ -1,199 +1,207 @@
1
  ---
2
- library_name: transformers
3
- tags: []
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
  ## Model Details
13
 
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
 
36
- ## Uses
37
 
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
 
40
- ### Direct Use
41
 
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
 
44
- [More Information Needed]
45
 
46
- ### Downstream Use [optional]
47
 
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
 
50
- [More Information Needed]
51
 
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
 
70
  ## How to Get Started with the Model
71
 
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
- ## Training Details
 
77
 
78
- ### Training Data
 
79
 
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 
 
 
 
81
 
82
- [More Information Needed]
 
 
83
 
84
- ### Training Procedure
85
 
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
 
87
 
88
- #### Preprocessing [optional]
89
 
90
- [More Information Needed]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
 
 
92
 
93
- #### Training Hyperparameters
94
 
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
 
 
 
 
 
96
 
97
- #### Speeds, Sizes, Times [optional]
 
98
 
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
 
 
 
100
 
101
- [More Information Needed]
 
102
 
103
- ## Evaluation
104
 
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
 
107
- ### Testing Data, Factors & Metrics
 
 
108
 
109
- #### Testing Data
110
 
111
- <!-- This should link to a Dataset Card if possible. -->
112
 
113
- [More Information Needed]
 
 
 
 
 
 
 
 
 
114
 
115
- #### Factors
116
 
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
 
119
- [More Information Needed]
120
 
121
- #### Metrics
 
122
 
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
 
125
- [More Information Needed]
 
126
 
127
- ### Results
 
128
 
129
- [More Information Needed]
130
 
131
- #### Summary
 
132
 
133
 
 
134
 
135
- ## Model Examination [optional]
 
 
 
136
 
137
- <!-- Relevant interpretability work for the model goes here -->
 
138
 
139
- [More Information Needed]
140
 
141
- ## Environmental Impact
 
142
 
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
 
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
146
 
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
 
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
 
175
  **BibTeX:**
176
 
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
 
195
- [More Information Needed]
196
 
197
- ## Model Card Contact
198
 
199
- [More Information Needed]
 
1
  ---
2
+ datasets:
3
+ - homebrewltd/instruction-speech-whispervq-v2
4
+ language:
5
+ - en
6
+ license: apache-2.0
7
+ tags:
8
+ - sound language model
9
  ---
10
 
 
 
 
 
 
 
11
  ## Model Details
12
 
13
+ We have developed and released the family [llama3s](https://huggingface.co/collections/homebrew-research/llama3-s-669df2139f0576abc6eb7405). This family is natively understanding audio and text input.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
 
15
+ We expand the Semantic tokens experiment with WhisperVQ as a tokenizer for audio files from [homebrewltd/llama3.1-s-base-v0.2](https://huggingface.co/homebrewltd/llama3.1-s-base-v0.2) with nearly 1B tokens from [Instruction Speech WhisperVQ v2](https://huggingface.co/datasets/homebrewltd/instruction-speech-whispervq-v2) dataset.
16
 
17
+ **Model developers** Homebrew Research.
18
 
19
+ **Input** Text and sound.
20
 
21
+ **Output** Text.
22
 
23
+ **Model Architecture** Llama-3.
24
 
25
+ **Language(s):** English.
26
 
27
+ ## Intended Use
28
 
29
+ **Intended Use Cases** This family is primarily intended for research applications. This version aims to further improve the LLM on sound understanding capabilities.
30
 
31
+ **Out-of-scope** The use of llama3-s in any manner that violates applicable laws or regulations is strictly prohibited.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
 
33
  ## How to Get Started with the Model
34
 
35
+ Try this model using [Google Colab Notebook](https://colab.research.google.com/drive/18IiwN0AzBZaox5o0iidXqWD1xKq11XbZ?usp=sharing).
36
+
37
+ First, we need to convert the audio file to sound tokens
38
+
39
+ ```python
40
+ device = "cuda" if torch.cuda.is_available() else "cpu"
41
+ if not os.path.exists("whisper-vq-stoks-medium-en+pl-fixed.model"):
42
+ hf_hub_download(
43
+ repo_id="jan-hq/WhisperVQ",
44
+ filename="whisper-vq-stoks-medium-en+pl-fixed.model",
45
+ local_dir=".",
46
+ )
47
+ vq_model = RQBottleneckTransformer.load_model(
48
+ "whisper-vq-stoks-medium-en+pl-fixed.model"
49
+ ).to(device)
50
+ def audio_to_sound_tokens(audio_path, target_bandwidth=1.5, device=device):
51
+ vq_model.ensure_whisper(device)
52
+
53
+ wav, sr = torchaudio.load(audio_path)
54
+ if sr != 16000:
55
+ wav = torchaudio.functional.resample(wav, sr, 16000)
56
+ with torch.no_grad():
57
+ codes = vq_model.encode_audio(wav.to(device))
58
+ codes = codes[0].cpu().tolist()
59
 
60
+ result = ''.join(f'<|sound_{num:04d}|>' for num in codes)
61
+ return f'<|sound_start|>{result}<|sound_end|>'
62
 
63
+ def audio_to_sound_tokens_transcript(audio_path, target_bandwidth=1.5, device=device):
64
+ vq_model.ensure_whisper(device)
65
 
66
+ wav, sr = torchaudio.load(audio_path)
67
+ if sr != 16000:
68
+ wav = torchaudio.functional.resample(wav, sr, 16000)
69
+ with torch.no_grad():
70
+ codes = vq_model.encode_audio(wav.to(device))
71
+ codes = codes[0].cpu().tolist()
72
 
73
+ result = ''.join(f'<|sound_{num:04d}|>' for num in codes)
74
+ return f'<|reserved_special_token_69|><|sound_start|>{result}<|sound_end|>'
75
+ ```
76
 
77
+ Then, we can inference the model the same as any other LLM.
78
 
79
+ ```python
80
+ def setup_pipeline(model_path, use_4bit=False, use_8bit=False):
81
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
82
 
83
+ model_kwargs = {"device_map": "auto"}
84
 
85
+ if use_4bit:
86
+ model_kwargs["quantization_config"] = BitsAndBytesConfig(
87
+ load_in_4bit=True,
88
+ bnb_4bit_compute_dtype=torch.bfloat16,
89
+ bnb_4bit_use_double_quant=True,
90
+ bnb_4bit_quant_type="nf4",
91
+ )
92
+ elif use_8bit:
93
+ model_kwargs["quantization_config"] = BitsAndBytesConfig(
94
+ load_in_8bit=True,
95
+ bnb_8bit_compute_dtype=torch.bfloat16,
96
+ bnb_8bit_use_double_quant=True,
97
+ )
98
+ else:
99
+ model_kwargs["torch_dtype"] = torch.bfloat16
100
 
101
+ model = AutoModelForCausalLM.from_pretrained(model_path, **model_kwargs)
102
 
103
+ return pipeline("text-generation", model=model, tokenizer=tokenizer)
104
 
105
+ def generate_text(pipe, messages, max_new_tokens=64, temperature=0.0, do_sample=False):
106
+ generation_args = {
107
+ "max_new_tokens": max_new_tokens,
108
+ "return_full_text": False,
109
+ "temperature": temperature,
110
+ "do_sample": do_sample,
111
+ }
112
 
113
+ output = pipe(messages, **generation_args)
114
+ return output[0]['generated_text']
115
 
116
+ # Usage
117
+ llm_path = "homebrewltd/llama3.1-s-instruct-v0.2"
118
+ pipe = setup_pipeline(llm_path, use_8bit=True)
119
+ ```
120
 
121
+ ## Training process
122
+ **Training Metrics Image**: Below is a snapshot of the training loss curve visualized.
123
 
124
+ ![training_](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/pQ8y9GoSvtv42MgkKRDt0.png)
125
 
126
+ ### Hardware
127
 
128
+ **GPU Configuration**: Cluster of 8x NVIDIA H100-SXM-80GB.
129
+ **GPU Usage**:
130
+ - **Continual Training**: 12 hours.
131
 
132
+ ### Training Arguments
133
 
134
+ We utilize [torchtune](https://github.com/pytorch/torchtune) library for the latest FSDP2 training code implementation.
135
 
136
+ | Parameter | Instruction Fine-tuning |
137
+ |----------------------------|-------------------------|
138
+ | **Epoch** | 1 |
139
+ | **Global batch size** | 128 |
140
+ | **Learning Rate** | 7e-5 |
141
+ | **Learning Scheduler** | Cosine with warmup |
142
+ | **Optimizer** | Adam torch fused |
143
+ | **Warmup Ratio** | 0.01 |
144
+ | **Weight Decay** | 0.005 |
145
+ | **Max Sequence Length** | 4096 |
146
 
 
147
 
148
+ ## Examples
149
 
150
+ 1. Good example:
151
 
152
+ <details>
153
+ <summary>Click to toggle Example 1</summary>
154
 
155
+ ```
156
 
157
+ ```
158
+ </details>
159
 
160
+ <details>
161
+ <summary>Click to toggle Example 2</summary>
162
 
163
+ ```
164
 
165
+ ```
166
+ </details>
167
 
168
 
169
+ 2. Misunderstanding example:
170
 
171
+ <details>
172
+ <summary>Click to toggle Example 3</summary>
173
+
174
+ ```
175
 
176
+ ```
177
+ </details>
178
 
179
+ 3. Off-tracked example:
180
 
181
+ <details>
182
+ <summary>Click to toggle Example 4</summary>
183
 
184
+ ```
185
 
186
+ ```
187
+ </details>
188
 
 
 
 
 
 
189
 
190
+ ## Citation Information
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
191
 
192
  **BibTeX:**
193
 
194
+ ```
195
+ @article{Llama3-S: Sound Instruction Language Model 2024,
196
+ title={Llama3-S},
197
+ author={Homebrew Research},
198
+ year=2024,
199
+ month=August},
200
+ url={https://huggingface.co/homebrewltd/llama3.1-s-2024-08-20}
201
+ ```
 
 
 
 
 
 
 
 
 
202
 
203
+ ## Acknowledgement
204
 
205
+ - **[WhisperSpeech](https://github.com/collabora/WhisperSpeech)**
206
 
207
+ - **[Meta-Llama-3.1-8B-Instruct ](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)**