Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "facebook/hf-seamless-m4t-medium",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "adaptor_dropout": 0.1,
+  "adaptor_kernel_size": 8,
+  "adaptor_stride": 8,
+  "add_adapter": true,
+  "architectures": [
+    "SeamlessM4TModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 2,
+  "conv_depthwise_kernel_size": 31,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.05,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 3,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.05,
+  "encoder_layers": 12,
+  "eos_token_id": 3,
+  "feature_projection_input_dim": 160,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "lang_embed_dim": 256,
+  "layer_norm_eps": 1e-05,
+  "leaky_relu_slope": 0.1,
+  "max_new_tokens": 256,
+  "max_position_embeddings": 4096,
+  "max_source_positions": 4096,
+  "model_type": "seamless_m4t",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embeddings_type": "relative",
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "rotary_embedding_base": 10000,
+  "sampling_rate": 16000,
+  "scale_embedding": true,
+  "speech_encoder_attention_heads": 16,
+  "speech_encoder_dropout": 0.0,
+  "speech_encoder_hidden_act": "swish",
+  "speech_encoder_intermediate_size": 4096,
+  "speech_encoder_layerdrop": 0.1,
+  "speech_encoder_layers": 12,
+  "spkr_embed_dim": 256,
+  "t2u_bos_token_id": 0,
+  "t2u_decoder_attention_heads": 16,
+  "t2u_decoder_ffn_dim": 8192,
+  "t2u_decoder_layers": 4,
+  "t2u_decoder_start_token_id": 2,
+  "t2u_encoder_attention_heads": 16,
+  "t2u_encoder_ffn_dim": 8192,
+  "t2u_encoder_layers": 4,
+  "t2u_eos_token_id": 2,
+  "t2u_max_new_tokens": 1024,
+  "t2u_max_position_embeddings": 2048,
+  "t2u_pad_token_id": 1,
+  "t2u_vocab_size": 10082,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "unit_embed_dim": 1280,
+  "unit_hifi_gan_vocab_size": 10000,
+  "upsample_initial_channel": 512,
+  "upsample_kernel_sizes": [
+    11,
+    8,
+    8,
+    4,
+    4
+  ],
+  "upsample_rates": [
+    5,
+    4,
+    4,
+    2,
+    2
+  ],
+  "use_cache": true,
+  "var_pred_dropout": 0.5,
+  "variance_predictor_kernel_size": 3,
+  "vocab_size": 256206,
+  "vocoder_num_langs": 36,
+  "vocoder_num_spkrs": 200,
+  "vocoder_offset": 4
+}

generation_config.json

@@ -0,0 +1,290 @@
+{
+  "bos_token_id": 2,
+  "decoder_start_token_id": 3,
+  "eos_token_id": 3,
+  "max_new_tokens": 256,
+  "pad_token_id": 0,
+  "t2u_lang_code_to_id": {
+    "arb": 10043,
+    "ben": 10044,
+    "cat": 10045,
+    "ces": 10046,
+    "cmn": 10047,
+    "cym": 10048,
+    "dan": 10049,
+    "deu": 10050,
+    "eng": 10051,
+    "est": 10052,
+    "fin": 10053,
+    "fra": 10054,
+    "hin": 10055,
+    "ind": 10056,
+    "ita": 10057,
+    "jpn": 10058,
+    "kan": 10059,
+    "kor": 10060,
+    "mlt": 10061,
+    "nld": 10062,
+    "pes": 10063,
+    "pol": 10064,
+    "por": 10065,
+    "ron": 10066,
+    "rus": 10067,
+    "slk": 10068,
+    "spa": 10069,
+    "swe": 10070,
+    "swh": 10071,
+    "tam": 10072,
+    "tel": 10073,
+    "tgl": 10074,
+    "tha": 10075,
+    "tur": 10076,
+    "ukr": 10077,
+    "urd": 10078,
+    "uzn": 10079,
+    "vie": 10080
+  },
+  "text_decoder_lang_to_code_id": {
+    "ace": 256001,
+    "ace_Latn": 256002,
+    "acm": 256003,
+    "acq": 256004,
+    "aeb": 256005,
+    "afr": 256006,
+    "ajp": 256007,
+    "aka": 256008,
+    "als": 256162,
+    "amh": 256009,
+    "apc": 256010,
+    "arb": 256011,
+    "ars": 256012,
+    "ary": 256013,
+    "arz": 256014,
+    "asm": 256015,
+    "ast": 256016,
+    "awa": 256017,
+    "ayr": 256018,
+    "azb": 256019,
+    "azj": 256020,
+    "bak": 256021,
+    "bam": 256022,
+    "ban": 256023,
+    "bel": 256024,
+    "bem": 256025,
+    "ben": 256026,
+    "bho": 256027,
+    "bjn": 256028,
+    "bjn_Latn": 256029,
+    "bod": 256030,
+    "bos": 256031,
+    "bug": 256032,
+    "bul": 256033,
+    "cat": 256034,
+    "ceb": 256035,
+    "ces": 256036,
+    "cjk": 256037,
+    "ckb": 256038,
+    "cmn": 256200,
+    "cmn_Hant": 256201,
+    "crh": 256039,
+    "cym": 256040,
+    "dan": 256041,
+    "deu": 256042,
+    "dik": 256043,
+    "dyu": 256044,
+    "dzo": 256045,
+    "ell": 256046,
+    "eng": 256047,
+    "epo": 256048,
+    "est": 256049,
+    "eus": 256050,
+    "ewe": 256051,
+    "fao": 256052,
+    "fij": 256054,
+    "fin": 256055,
+    "fon": 256056,
+    "fra": 256057,
+    "fur": 256058,
+    "fuv": 256059,
+    "gaz": 256135,
+    "gla": 256060,
+    "gle": 256061,
+    "glg": 256062,
+    "grn": 256063,
+    "guj": 256064,
+    "hat": 256065,
+    "hau": 256066,
+    "heb": 256067,
+    "hin": 256068,
+    "hne": 256069,
+    "hrv": 256070,
+    "hun": 256071,
+    "hye": 256072,
+    "ibo": 256073,
+    "ilo": 256074,
+    "ind": 256075,
+    "isl": 256076,
+    "ita": 256077,
+    "jav": 256078,
+    "jpn": 256079,
+    "kab": 256080,
+    "kac": 256081,
+    "kam": 256082,
+    "kan": 256083,
+    "kas": 256084,
+    "kas_Deva": 256085,
+    "kat": 256086,
+    "kaz": 256089,
+    "kbp": 256090,
+    "kea": 256091,
+    "khk": 256122,
+    "khm": 256092,
+    "kik": 256093,
+    "kin": 256094,
+    "kir": 256095,
+    "kmb": 256096,
+    "kmr": 256099,
+    "knc": 256087,
+    "knc_Latn": 256088,
+    "kon": 256097,
+    "kor": 256098,
+    "lao": 256100,
+    "lij": 256102,
+    "lim": 256103,
+    "lin": 256104,
+    "lit": 256105,
+    "lmo": 256106,
+    "ltg": 256107,
+    "ltz": 256108,
+    "lua": 256109,
+    "lug": 256110,
+    "luo": 256111,
+    "lus": 256112,
+    "lvs": 256101,
+    "mag": 256113,
+    "mai": 256114,
+    "mal": 256115,
+    "mar": 256116,
+    "min": 256117,
+    "mkd": 256118,
+    "mlt": 256120,
+    "mni": 256121,
+    "mos": 256123,
+    "mri": 256124,
+    "mya": 256126,
+    "nld": 256127,
+    "nno": 256128,
+    "nob": 256129,
+    "npi": 256130,
+    "nso": 256131,
+    "nus": 256132,
+    "nya": 256133,
+    "oci": 256134,
+    "ory": 256136,
+    "pag": 256137,
+    "pan": 256138,
+    "pap": 256139,
+    "pbt": 256143,
+    "pes": 256053,
+    "plt": 256119,
+    "pol": 256140,
+    "por": 256141,
+    "prs": 256142,
+    "quy": 256144,
+    "ron": 256145,
+    "run": 256146,
+    "rus": 256147,
+    "sag": 256148,
+    "san": 256149,
+    "sat": 256150,
+    "scn": 256151,
+    "shn": 256152,
+    "sin": 256153,
+    "slk": 256154,
+    "slv": 256155,
+    "smo": 256156,
+    "sna": 256157,
+    "snd": 256158,
+    "som": 256159,
+    "sot": 256160,
+    "spa": 256161,
+    "srd": 256163,
+    "srp": 256164,
+    "ssw": 256165,
+    "sun": 256166,
+    "swe": 256167,
+    "swh": 256168,
+    "szl": 256169,
+    "tam": 256170,
+    "taq": 256177,
+    "taq_Tfng": 256178,
+    "tat": 256171,
+    "tel": 256172,
+    "tgk": 256173,
+    "tgl": 256174,
+    "tha": 256175,
+    "tir": 256176,
+    "tpi": 256179,
+    "tsn": 256180,
+    "tso": 256181,
+    "tuk": 256182,
+    "tum": 256183,
+    "tur": 256184,
+    "twi": 256185,
+    "tzm": 256186,
+    "uig": 256187,
+    "ukr": 256188,
+    "umb": 256189,
+    "urd": 256190,
+    "uzn": 256191,
+    "vec": 256192,
+    "vie": 256193,
+    "war": 256194,
+    "wol": 256195,
+    "xho": 256196,
+    "ydd": 256197,
+    "yor": 256198,
+    "yue": 256199,
+    "zsm": 256125,
+    "zul": 256202
+  },
+  "transformers_version": "4.44.2",
+  "vocoder_lang_code_to_id": {
+    "arb": 0,
+    "ben": 1,
+    "cat": 2,
+    "ces": 3,
+    "cmn": 4,
+    "cym": 5,
+    "dan": 6,
+    "deu": 7,
+    "eng": 8,
+    "est": 9,
+    "fin": 10,
+    "fra": 11,
+    "hin": 12,
+    "ind": 13,
+    "ita": 14,
+    "jpn": 15,
+    "kor": 16,
+    "mlt": 17,
+    "nld": 18,
+    "pes": 19,
+    "pol": 20,
+    "por": 21,
+    "ron": 22,
+    "rus": 23,
+    "slk": 24,
+    "spa": 25,
+    "swe": 26,
+    "swh": 27,
+    "tel": 28,
+    "tgl": 29,
+    "tha": 30,
+    "tur": 31,
+    "ukr": 32,
+    "urd": 33,
+    "uzn": 34,
+    "vie": 35
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc11dbd8127b83b840965c86c56137dd523fd5da88f8a73f39603849e72016e
+size 4838113416